* Add latents nodes.
* Fix iteration expansion.
* Add collection generator nodes, math nodes.
* Add noise node.
* Add some graph debug commands to the CLI.
* Fix negative id linking in CLI.
* Fix a CLI bug with multiple links per node.
The typo accidentally did not affect functionality; when `query==""`, it
`search()`ed but found everything due to empty query, then paginated
results, so it worked the same as `list()`.
Still fix it
currently if users input eg `happy (camper:0.3)` it gets parsed
incorrectly, which causes crashes if it's in the negative prompt. bump
to compel 1.0.5 fixes the parser to avoid this (note the weight is
parsed as plain text, it's not converted to proper invoke syntax)
- This PR adds support for embedding files that contain a single key
"emb_params". The only example I know of this format is the
"EasyNegative" embedding on HuggingFace, but there are certainly others.
- This PR also adds support for loading embedding files that have been
saved in safetensors format.
- It also cleans up the code so that the logic of probing for and
selecting the right format parser is clear.
- This is the same as #3045, which is on the 2.3 branch.
- Commands, invocations and their parameters will now autocomplete using
introspection.
- Two types of parameter *arguments* will also autocomplete:
- --sampler_name will autocomplete the scheduler name
- --model will autocomplete the model name
- There don't seem to be commands for reading/writing image files yet,
so path autocompletion is not implemented
A long-standing issue with importing legacy checkpoints (both ckpt and
safetensors) is that the user has to identify the correct config file,
either by providing its path or by selecting which type of model the
checkpoint is (e.g. "v1 inpainting"). In addition, some users wish to
provide custom VAEs for use with the model. Currently this is done in
the WebUI by importing the model, editing it, and then typing in the
path to the VAE.
## Model configuration file selection
To improve the user experience, the model manager's `heuristic_import()`
method has been enhanced as follows:
1. When initially called, the caller can pass a config file path, in
which case it will be used.
2. If no config file provided, the method looks for a .yaml file in the
same directory as the model which bears the same basename. e.g.
```
my-new-model.safetensors
my-new-model.yaml
```
The yaml file is then used as the configuration file for importation and
conversion.
3. If no such file is found, then the method opens up the checkpoint and
probes it to determine whether it is V1, V1-inpaint or V2. If it is a V1
format, then the appropriate v1-inference.yaml config file is used.
Unfortunately there are two V2 variants that cannot be distinguished by
introspection.
4. If the probe algorithm is unable to determine the model type, then
its last-ditch effort is to execute an optional callback function that
can be provided by the caller. This callback, named
`config_file_callback` receives the path to the legacy checkpoint and
returns the path to the config file to use. The CLI uses to put up a
multiple choice prompt to the user. The WebUI **could** use this to
prompt the user to choose from a radio-button selection.
5. If the config file cannot be determined, then the import is
abandoned.
## Custom VAE Selection
The user can attach a custom VAE to the imported and converted model by
copying the desired VAE into the same directory as the file to be
imported, and giving it the same basename. E.g.:
```
my-new-model.safetensors
my-new-model.vae.pt
```
For this to work, the VAE must end with ".vae.pt", ".vae.ckpt", or
".vae.safetensors". The indicated VAE will be converted into diffusers
format and stored with the converted models file, so the ".pt" file can
be deleted after conversion.
No facility is currently provided to swap a diffusers VAE at import
time, but this can be done after the fact using the WebUI and CLI's
model editing functions.
Note that this is the same fix that was applied to the 2.3 branch in
#3043 . This applies to `main`.
## Enable the on-the-fly conversion of models based on SD 2.0/2.1 into
diffusers
This commit fixes bugs related to the on-the-fly conversion and loading
of legacy checkpoint models built on SD-2.0 base.
- When legacy checkpoints built on SD-2.0 models were converted
on-the-fly using --ckpt_convert, generation would crash with a precision
incompatibility error. This problem has been found and fixed.
This commit fixes bugs related to the on-the-fly conversion and loading of
legacy checkpoint models built on SD-2.0 base.
- When legacy checkpoints built on SD-2.0 models were converted
on-the-fly using --ckpt_convert, generation would crash with a
precision incompatibility error.
The Pytorch ROCm version in the documentation in outdated (`rocm5.2`)
which leads to errors during the installation of InvokeAI.
This PR updates the documentation with the latest Pytorch ROCm `5.4.2`
version.
A long-standing issue with importing legacy checkpoints (both ckpt and
safetensors) is that the user has to identify the correct config file,
either by providing its path or by selecting which type of model the
checkpoint is (e.g. "v1 inpainting"). In addition, some users wish to
provide custom VAEs for use with the model. Currently this is done in
the WebUI by importing the model, editing it, and then typing in the
path to the VAE.
To improve the user experience, the model manager's
`heuristic_import()` method has been enhanced as follows:
1. When initially called, the caller can pass a config file path, in
which case it will be used.
2. If no config file provided, the method looks for a .yaml file in the
same directory as the model which bears the same basename. e.g.
```
my-new-model.safetensors
my-new-model.yaml
```
The yaml file is then used as the configuration file for
importation and conversion.
3. If no such file is found, then the method opens up the checkpoint
and probes it to determine whether it is V1, V1-inpaint or V2.
If it is a V1 format, then the appropriate v1-inference.yaml config
file is used. Unfortunately there are two V2 variants that cannot be
distinguished by introspection.
4. If the probe algorithm is unable to determine the model type, then its
last-ditch effort is to execute an optional callback function that can
be provided by the caller. This callback, named `config_file_callback`
receives the path to the legacy checkpoint and returns the path to the
config file to use. The CLI uses to put up a multiple choice prompt to
the user. The WebUI **could** use this to prompt the user to choose
from a radio-button selection.
5. If the config file cannot be determined, then the import is abandoned.
The user can attach a custom VAE to the imported and converted model
by copying the desired VAE into the same directory as the file to be
imported, and giving it the same basename. E.g.:
```
my-new-model.safetensors
my-new-model.vae.pt
```
For this to work, the VAE must end with ".vae.pt", ".vae.ckpt", or
".vae.safetensors". The indicated VAE will be converted into diffusers
format and stored with the converted models file, so the ".pt" file
can be deleted after conversion.
No facility is currently provided to swap a diffusers VAE at import
time, but this can be done after the fact using the WebUI and CLI's
model editing functions.
- This PR adds support for embedding files that contain a single key
"emb_params". The only example I know of this format is the
"EasyNegative" embedding on HuggingFace, but there are certainly
others.
- This PR also adds support for loading embedding files that have been
saved in safetensors format.
- It also cleans up the code so that the logic of probing for and
selecting the right format parser is clear.
keeping `main` up to date with my api nodes branch:
- bd7e515290: [nodes] Add cancelation to
the API @Kyle0654
- 5fe38f7: fix(backend): simple typing fixes
- just picking some low-hanging fruit to improve IDE hinting
- c34ac91: fix(nodes): fix cancel; fix callback for img2img, inpaint
- makes nodes cancel immediate, use fix progress images on nodes, fix
callbacks for img2img/inpaint
- 4221cf7: fix(nodes): fix schema generation for output classes
- did this previously for some other class; needed to not have node
outputs be optional
Some schedulers report not only the noisy latents at the current
timestep, but also their estimate so far of what the de-noised latents
will be.
It makes for a more legible preview than the noisy latents do.
I think this is a huge improvement, but there are a few considerations:
- Need to not spook @JPPhoto by changing how previews look.
- Some schedulers (most notably **DPM Solver++**) don't provide this
data, and it falls back to the current behavior there. That's not
terrible, but seeing such a big difference in how _previews_ look from
one scheduler to the next might mislead people into thinking there's a
bigger difference in their overall effectiveness than there really is.
My fear of configuration-option-overwhelm leaves me inclined to _not_
add a configuration option for this, but we could.
- Commands, invocations and their parameters will now autocomplete
using introspection.
- Two types of parameter *arguments* will also autocomplete:
- --sampler_name will autocomplete the scheduler name
- --model will autocomplete the model name
- There don't seem to be commands for reading/writing image files yet, so
path autocompletion is not implemented
- resolve conflicts with generate.py invocation
- remove unused symbols that pyflakes complains about
- add **untested** code for passing intermediate latent image to the
step callback in the format expected.
This PR fixes#2951 and restores the step_callback argument in the
refactored generate() method. Note that this issue states that
"something is still wrong because steps and step are zero." However,
I think this is confusion over the call signature of the callback, which
since the diffusers merge has been `callback(state:PipelineIntermediateState)`
This is the test script that I used to determine that `step` is being passed
correctly:
```
from pathlib import Path
from invokeai.backend import ModelManager, PipelineIntermediateState
from invokeai.backend.globals import global_config_dir
from invokeai.backend.generator import Txt2Img
def my_callback(state:PipelineIntermediateState, total_steps:int):
print(f'callback(step={state.step}/{total_steps})')
def main():
manager = ModelManager(Path(global_config_dir()) / "models.yaml")
model = manager.get_model('stable-diffusion-1.5')
print ('=== TXT2IMG TEST ===')
steps=30
output = next(Txt2Img(model).generate(prompt='banana sushi',
iterations=None,
steps=steps,
step_callback=lambda x: my_callback(x,steps)
)
)
print(f'image={output.image}, seed={output.seed}, steps={output.params.steps}')
if __name__=='__main__':
main()
```
- When a legacy checkpoint model is loaded via --convert_ckpt and its
models.yaml stanza refers to a custom VAE path (using the 'vae:' key),
the custom VAE will be converted and used within the diffusers model.
Otherwise the VAE contained within the legacy model will be used.
- Note that the checkpoint import functions in the CLI or Web UIs
continue to default to the standard stabilityai/sd-vae-ft-mse VAE. This
can be fixed after the fact by editing VAE key using either the CLI or
Web UI.
- Fixes issue #2917
The mkdocs-workflow has been failing over the past week due to
permission denied errors. I *think* this is the result of not passing
the GitHub API token to the workflow, and this is a speculative fix for
the issue.
- This PR turns on pickle scanning before a legacy checkpoint file is
loaded from disk within the checkpoint_to_diffusers module.
- Also miscellaneous diagnostic message cleanup.
- See also #3011 for a similar patch to the 2.3 branch.
Currently translated at 100.0% (504 of 504 strings)
translationBot(ui): update translation (Spanish)
Currently translated at 100.0% (501 of 501 strings)
Co-authored-by: gallegonovato <fran-carro@hotmail.es>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/es/
Translation: InvokeAI/Web UI
Currently translated at 100.0% (504 of 504 strings)
translationBot(ui): update translation (Italian)
Currently translated at 100.0% (501 of 501 strings)
translationBot(ui): update translation (Italian)
Currently translated at 100.0% (500 of 500 strings)
Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI
This PR fixes#2951 and restores the step_callback argument in the
refactored generate() method. Note that this issue states that
"something is still wrong because steps and step are zero." However,
I think this is confusion over the call signature of the callback, which
since the diffusers merge has been `callback(state:PipelineIntermediateState)`
This is the test script that I used to determine that `step` is being passed
correctly:
```
from pathlib import Path
from invokeai.backend import ModelManager, PipelineIntermediateState
from invokeai.backend.globals import global_config_dir
from invokeai.backend.generator import Txt2Img
def my_callback(state:PipelineIntermediateState, total_steps:int):
print(f'callback(step={state.step}/{total_steps})')
def main():
manager = ModelManager(Path(global_config_dir()) / "models.yaml")
model = manager.get_model('stable-diffusion-1.5')
print ('=== TXT2IMG TEST ===')
steps=30
output = next(Txt2Img(model).generate(prompt='banana sushi',
iterations=None,
steps=steps,
step_callback=lambda x: my_callback(x,steps)
)
)
print(f'image={output.image}, seed={output.seed}, steps={output.params.steps}')
if __name__=='__main__':
main()
```
This PR corrects a bug in which embeddings were not being applied when a
non-diffusers model was loaded.
- Fixes#2954
- Also improves diagnostic reporting during embedding loading.
- This PR turns on pickle scanning before a legacy checkpoint file
is loaded from disk within the checkpoint_to_diffusers module.
- Also miscellaneous diagnostic message cleanup.
- When a legacy checkpoint model is loaded via --convert_ckpt and its
models.yaml stanza refers to a custom VAE path (using the 'vae:'
key), the custom VAE will be converted and used within the diffusers
model. Otherwise the VAE contained within the legacy model will be
used.
- Note that the heuristic_import() method, which imports arbitrary
legacy files on disk and URLs, will continue to default to the
the standard stabilityai/sd-vae-ft-mse VAE. This can be fixed after
the fact by editing the models.yaml stanza using the Web or CLI
UIs.
- Fixes issue #2917
- 86932469e76f1315ee18bfa2fc52b588241dace1 add image_to_dataURL util
- 0c2611059711b45bb6142d30b1d1343ac24268f3 make fast latents method
static
- this method doesn't really need `self` and should be able to be called
without instantiating `Generator`
- 2360bfb6558ea511e9c9576f3d4b5535870d84b4 fix schema gen for
GraphExecutionState
- `GraphExecutionState` uses `default_factory` in its fields; the result
is the OpenAPI schema marks those fields as optional, which propagates
to the generated API client, which means we need a lot of unnecessary
type guards to use this data type. the [simple
fix](https://github.com/pydantic/pydantic/discussions/4577) is to add
config to explicitly say all class properties are required. looks this
this will be resolved in a future pydantic release
- 3cd7319cfdb0f07c6bb12d62d7d02efe1ab12675 fix step callback and fast
latent generation on nodes. have this working in UI. depends on the
small change in #2957
Update `compel` to 1.0.0.
This fixes#2832.
It also changes the way downweighting is applied. In particular,
downweighting should now be much better and more controllable.
From the [compel
changelog](https://github.com/damian0815/compel#changelog):
> Downweighting now works by applying an attention mask to remove the
downweighted tokens, rather than literally removing them from the
sequence. This behaviour is the default, but the old behaviour can be
re-enabled by passing `downweight_mode=DownweightMode.REMOVE` on init of
the `Compel` instance.
>
> Formerly, downweighting a token worked by both multiplying the
weighting of the token's embedding, and doing an inverse-weighted blend
with a copy of the token sequence that had the downweighted tokens
removed. The intuition is that as weight approaches zero, the tokens
being downweighted should be actually removed from the sequence.
However, removing the tokens resulted in the positioning of all
downstream tokens becoming messed up. The blend ended up blending a lot
more than just the tokens in question.
>
> As of v1.0.0, taking advice from @keturn and @bonlime
(https://github.com/damian0815/compel/issues/7) the procedure is by
default different. Downweighting still involves a blend but what is
blended is a version of the token sequence with the downweighted tokens
masked out, rather than removed. This correctly preserves positioning
embeddings of the other tokens.
* Update root component to allow optional children that will render as
dynamic header of UI
* Export additional components (logo & themeChanger) for use in said
dynamic header (more to come here)
# The Problem
Pickle files (.pkl, .ckpt, etc) are extremely unsafe as they can be
trivially crafted to execute arbitrary code when parsed using
`torch.load`
Right now the conventional wisdom among ML researchers and users is to
simply `not run untrusted pickle files ever` and instead only use
Safetensor files, which cannot be injected with arbitrary code. This is
very good advice.
Unfortunately, **I have discovered a vulnerability inside of InvokeAI
that allows an attacker to disguise a pickle file as a safetensor and
have the payload execute within InvokeAI.**
# How It Works
Within `model_manager.py` and `convert_ckpt_to_diffusers.py` there are
if-statements that decide which `load` method to use based on the file
extension of the model file. The logic (written in a slightly more
readable format than it exists in the codebase) is as follows:
```
if Path(file).suffix == '.safetensors':
safetensor_load(file)
else:
unsafe_pickle_load(file)
```
A malicious actor would only need to create an infected .ckpt file, and
then rename the extension to something that does not pass the `==
'.safetensors'` check, but still appears to a user to be a safetensors
file.
For example, this might be something like `.Safetensors`,
`.SAFETENSORS`, `SafeTensors`, etc.
InvokeAI will happily import the file in the Model Manager and execute
the payload.
# Proof of Concept
1. Create a malicious pickle file.
(https://gist.github.com/CodeZombie/27baa20710d976f45fb93928cbcfe368)
2. Rename the `.ckpt` extension to some variation of `.Safetensors`,
ensuring there is a capital letter anywhere in the extension (eg.
`malicious_pickle.SAFETENSORS`)
3. Import the 'model' like you would normally with any other safetensors
file with the Model Manager.
4. Upon trying to select the model in the web ui, it will be loaded (or
attempt to be converted to a Diffuser) with `torch.load` and the payload
will execute.
# The Fix
This pull request changes the logic InvokeAI uses to decide which model
loader to use so that the safe behavior is the default. Instead of
loading as a pickle if the extension is not exactly `.safetensors`, it
will now **always** load as a safetensors file unless the extension is
**exactly** `.ckpt`.
# Notes:
I think support for pickle files should be totally dropped ASAP as a
matter of security, but I understand that there are reasons this would
be difficult.
In the meantime, I think `RestrictedUnpickler` or something similar
should be implemented as a replacement for `torch.load`, as this
significantly reduces the amount of Python methods that an attacker has
to work with when crafting malicious payloads
inside a pickle file.
Automatic1111 already uses this with some success.
(https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/modules/safe.py)
- The value of png_compression was always 6, despite the value provided
to the --png_compression argument. This fixes the bug.
- It also fixes an inconsistency between the maximum range of
png_compression and the help text.
- Closes#2945
- The value of png_compression was always 6, despite the value provided to the
--png_compression argument. This fixes the bug.
- It also fixes an inconsistency between the maximum range of png_compression
and the help text.
- Closes#2945
Prior to this commit, all models would be loaded with the extremely unsafe `torch.load` method, except those with the exact extension `.safetensors`. Even a change in casing (eg. `saFetensors`, `Safetensors`, etc) would cause the file to be loaded with torch.load instead of the much safer `safetensors.toch.load_file`.
If a malicious actor renamed an infected `.ckpt` to something like `.SafeTensors` or `.SAFETENSORS` an unsuspecting user would think they are loading a safe .safetensor, but would in fact be parsing an unsafe pickle file, and executing an attacker's payload. This commit fixes this vulnerability by reversing the loading-method decision logic to only use the unsafe `torch.load` when the file extension is exactly `.ckpt`.
#2931 was caused by new code that held onto the PRNG in `get_make_image`
and used it in `make_image` for img2img and inpainting. This
functionality has been moved elsewhere so that we can generate multiple
images again.
fix(ui): remove old scrollbar css
fix(ui): make guidepopover lazy
feat(ui): wip resizable drawer
feat(ui): wip resizable drawer
feat(ui): add scroll-linked shadow
feat(ui): organize files
Align Scrollbar next to content
Move resizable drawer underneath the progress bar
Add InvokeLogo to unpinned & align
Adds Invoke Logo to Unpinned Parameters panel and aligns to make it feel seamless.
# Remove node dependencies on generate.py
This is a draft PR in which I am replacing `generate.py` with a cleaner,
more structured interface to the underlying image generation routines.
The basic code pattern to generate an image using the new API is this:
```
from invokeai.backend import ModelManager, Txt2Img, Img2Img
manager = ModelManager('/data/lstein/invokeai-main/configs/models.yaml')
model = manager.get_model('stable-diffusion-1.5')
txt2img = Txt2Img(model)
outputs = txt2img.generate(prompt='banana sushi', steps=12, scheduler='k_euler_a', iterations=5)
# generate() returns an iterator
for next_output in outputs:
print(next_output.image, next_output.seed)
outputs = Img2Img(model).generate(prompt='strawberry` sushi', init_img='./banana_sushi.png')
output = next(outputs)
output.image.save('strawberries.png')
```
### model management
The `ModelManager` handles model selection and initialization. Its
`get_model()` method will return a `dict` with the following keys:
`model`, `model_name`,`hash`, `width`, and `height`, where `model` is
the actual StableDiffusionGeneratorPIpeline. If `get_model()` is called
without a model name, it will return whatever is defined as the default
in `models.yaml`, or the first entry if no default is designated.
### InvokeAIGenerator
The abstract base class `InvokeAIGenerator` is subclassed into into
`Txt2Img`, `Img2Img`, `Inpaint` and `Embiggen`. The constructor for
these classes takes the model dict returned by
`model_manager.get_model()` and optionally an
`InvokeAIGeneratorBasicParams` object, which encapsulates all the
parameters in common among `Txt2Img`, `Img2Img` etc. If you don't
provide the basic params, a reasonable set of defaults will be chosen.
Any of these parameters can be overridden at `generate()` time.
These classes are defined in `invokeai.backend.generator`, but they are
also exported by `invokeai.backend` as shown in the example below.
```
from invokeai.backend import InvokeAIGeneratorBasicParams, Img2Img
params = InvokeAIGeneratorBasicParams(
perlin = 0.15
steps = 30
scheduler = 'k_lms'
)
img2img = Img2Img(model, params)
outputs = img2img.generate(scheduler='k_heun')
```
Note that we were able to override the basic params in the call to
`generate()`
The `generate()` method will returns an iterator over a series of
`InvokeAIGeneratorOutput` objects. These objects contain the PIL image,
the seed, the model name and hash, and attributes for all the parameters
used to generate the object (you can also get these as a dict). The
`iterations` argument controls how many objects will be returned,
defaulting to 1. Pass `None` to get an infinite iterator.
Given the proposed use of `compel` to generate a templated series of
prompts, I thought the API would benefit from a style that lets you loop
over the output results indefinitely. I did consider returning a single
`InvokeAIGeneratorOutput` object in the event that `iterations=1`, but I
think it's dangerous for a method to return different types of result
under different circumstances.
Changing the model is as easy as this:
```
model = manager.get_model('inkspot-2.0`)
txt2img = Txt2Img(model)
```
### Node and legacy support
With respect to `Nodes`, I have written `model_manager_initializer` and
`restoration_services` modules that return `model_manager` and
`restoration` services respectively. The latter is used by the face
reconstruction and upscaling nodes. There is no longer any reference to
`Generate` in the `app` tree.
I have confirmed that `txt2img` and `img2img` work in the nodes client.
I have not tested `embiggen` or `inpaint` yet. pytests are passing, with
some warnings that I don't think are related to what I did.
The legacy WebUI and CLI are still working off `Generate` (which has not
yet been removed from the source tree) and fully functional.
I've finished all the tasks on my TODO list:
- [x] Update the pytests, which are failing due to dangling references
to `generate`
- [x] Rewrite the `reconstruct.py` and `upscale.py` nodes to call
directly into the postprocessing modules rather than going through
`Generate`
- [x] Update the pytests, which are failing due to dangling references
to `generate`
Prior to the folder restructure, the `paths` for `test-invoke-pip` did
not include the UI's path `invokeai/frontend/`:
```yaml
paths:
- 'pyproject.toml'
- 'ldm/**'
- 'invokeai/backend/**'
- 'invokeai/configs/**'
- 'invokeai/frontend/dist/**'
```
After the restructure, more code was moved into the `invokeai/frontend/`
folder, and `paths` was updated:
```yaml
paths:
- 'pyproject.toml'
- 'invokeai/**'
- 'invokeai/backend/**'
- 'invokeai/configs/**'
- 'invokeai/frontend/web/dist/**'
```
Now, the second path includes the UI. The UI now needs to be excluded,
and must be excluded prior to `invokeai/frontend/web/dist/**` being
included.
On `test-invoke-pip-skip`, we need to do a bit of logic juggling to
invert the folder selection. First, include the web folder, then exclude
everying around it and finally exclude the `dist/` folder
Currently translated at 100.0% (500 of 500 strings)
translationBot(ui): update translation (Italian)
Currently translated at 100.0% (500 of 500 strings)
translationBot(ui): update translation (Italian)
Currently translated at 100.0% (482 of 482 strings)
translationBot(ui): update translation (Italian)
Currently translated at 100.0% (480 of 480 strings)
Co-authored-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/it/
Translation: InvokeAI/Web UI
Currently translated at 100.0% (500 of 500 strings)
translationBot(ui): update translation (Spanish)
Currently translated at 100.0% (482 of 482 strings)
translationBot(ui): update translation (Spanish)
Currently translated at 100.0% (480 of 480 strings)
Co-authored-by: gallegonovato <fran-carro@hotmail.es>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/es/
Translation: InvokeAI/Web UI
Cause of the problem was inadvertent activation of the safety checker.
When conversion occurs on disk, the safety checker is disabled during loading.
However, when converting in RAM, the safety checker was not removed, resulting
in it activating even when user specified --no-nsfw_checker.
This PR fixes the problem by detecting when the caller has requested the InvokeAi
StableDiffusionGeneratorPipeline class to be returned and setting safety checker
to None. Do not do this with diffusers models destined for disk because then they
will be incompatible with the merge script!!
Closes#2836
Some schedulers report not only the noisy latents at the current timestep,
but also their estimate so far of what the de-noised latents will be.
It makes for a more legible preview than the noisy latents do.
Reverts invoke-ai/InvokeAI#2903
@mauwii has a point here. It looks like triggering on a comment results
in an action for each of the stale issues, even ones that have been
previously dealt with. I'd like to revert this back to the original
behavior of running once every time the cron job executes.
What's the original motivation for having more frequent labeling of the
issues?
I found it to be a chore to remove labels manually in order to
"un-stale" issues. This is contrary to the bot message which says
commenting should remove "stale" status. On the current `cron` schedule,
there may be a delay of up to 24 hours before the label is removed. This
PR will trigger the workflow on issue comments in addition to the
schedule.
Also adds a condition to not run this job on PRs (Github treats issues
and PRs equivalently in this respect), and rewords the messages for
clarity.
This ought to be working but i don't know how it's supposed to behave so
i haven't been able to verify. At least, I know the numbers are getting
pushed all the way to the SD unet, i just have been unable to verify if
what's coming out is what is expected. Please test.
You'll `need to pip install -e .` after switching to the branch, because
it's currently pulling from a non-main `compel` branch. Once it's
verified as working as intended i'll promote the compel branch to pypi.
# Overview
Adding a few accessibility items (I think 9 total items). Mostly
`aria-label`, but also a `<VisuallyHidden>` to the left-side nav tab
icons. Tried to match existing copy that was being used. Feedback
welcome
* Fix img2img and inpainting code so a strength of 1 behaves the same as txt2img.
* Make generated images identical to their txt2img counterparts when strength is 1.
Updates the CLI to define CLI commands as Pydantic objects, similar to
how Invocations (nodes) work. For example:
```py
class HelpCommand(BaseCommand):
"""Shows help"""
type: Literal['help'] = 'help'
def run(self, context: CliContext) -> None:
context.parser.print_help()
```
*looks like this #2814 was reverted accidentally. instead of trying to
revert the revert, this PR can simply be re-accepted and will fix the
ui.*
- Migrate UI from SCSS to Chakra's CSS-in-JS system
- better dx
- more capable theming
- full RTL language support (we now have Arabic and Hebrew)
- general cleanup of the whole UI's styling
- Tidy npm packages and update scripts, necessitates update to github
actions
To test this PR in dev mode, you will need to do a `yarn install` as a
lot has changed.
thanks to @blessedcoolant for helping out on this, it was a big effort.
There are actually two Stable Diffusion v2 legacy checkpoint
configurations:
1. "epsilon" prediction type for Stable Diffusion v2 Base
2. "v-prediction" type for Stable Diffusion v2-768
This commit adds the configuration file needed for epsilon prediction
type models as well as the UI that prompts the user to select the
appropriate configuration file when the code can't do so automatically.
To avoid `git blame` recording all the autoformatting changes under the
name 'lstein', this PR adds a `.git-blame-ignore-revs` that will ignore
any provenance changes that occurred during the recent refactor merge.
This fixes the crash that was occurring when trying to load a legacy
checkpoint file.
Note that this PR includes commits from #2867 to avoid diffusers files
from re-downloading at startup time.
There are actually two Stable Diffusion v2 legacy checkpoint
configurations:
1) "epsilon" prediction type for Stable Diffusion v2 Base
2) "v-prediction" type for Stable Diffusion v2-768
This commit adds the configuration file needed for epsilon prediction
type models as well as the UI that prompts the user to select the
appropriate configuration file when the code can't do so
automatically.
# Migrate to new HF diffusers cache location
This PR adjusts the model cache directory to use the layout of
`diffusers 0.14`. This will automatically migrate any diffusers models
located in `INVOKEAI_ROOT/models/diffusers` to
`INVOKEAI_ROOT/models/hub`, and cache new downloaded diffusers files
into the same location.
As before, if environment variable `HF_HOME` is set, then both
HuggingFace `from_pretrained()` calls as well as all InvokeAI methods
will use `HF_HOME/hub` as their cache.
- Migrate UI from SCSS to Chakra's CSS-in-JS system
- better dx
- more capable theming
- full RTL language support (we now have Arabic and Hebrew)
- general cleanup of the whole UI's styling
- Tidy npm packages and update scripts, necessitates update to github
actions
To test this PR in dev mode, you will need to do a `yarn install` as a
lot has changed.
thanks to @blessedcoolant for helping out on this, it was a big effort.
This removes modules that appear to be no longer used by any code under
the `invokeai` package now that the `ckpt_generator` is gone.
There are a few small changes in here to code that was referencing code
in a conditional branch for ckpt, or to swap out a ⚡ function for a
🤗 one, but only as much was strictly necessary to get things to
run. We'll follow with more clean-up to get lingering `if isinstance` or
`except AttributeError` branches later.
build(ui): fix husky path
build(ui): fix hmr issue, remove emotion cache
build(ui): clean up package.json
build(ui): update gh action and npm scripts
feat(ui): wip port lightbox to chakra theme
feat(ui): wip use chakra theme tokens
feat(ui): Add status text to main loading spinner
feat(ui): wip chakra theme tweaking
feat(ui): simply iaisimplemenu button
feat(ui): wip chakra theming
feat(ui): Theme Management
feat(ui): Add Ocean Blue Theme
feat(ui): wip lightbox
fix(ui): fix lightbox mouse
feat(ui): set default theme variants
feat(ui): model manager chakra theme
chore(ui): lint
feat(ui): remove last scss
feat(ui): fix switch theme
feat(ui): Theme Cleanup
feat(ui): Stylize Search Models Found List
feat(ui): hide scrollbars
feat(ui): fix floating button position
feat(ui): Scrollbar Styling
fix broken scripts
This PR fixes the following scripts:
1) Scripts that can be executed within the repo's scripts directory.
Note that these are for development testing and are not intended
to be exposed to the user.
configure_invokeai.py - configuration
dream.py - the legacy CLI
images2prompt.py - legacy "dream prompt" retriever
invoke-new.py - new nodes-based CLI
invoke.py - the legacy CLI under another name
make_models_markdown_table.py - a utility used during the release/doc process
pypi_helper.py - another utility used during the release process
sd-metadata.py - retrieve JSON-formatted metadata from a PNG file
2) Scripts that are installed by pip install. They get placed into the venv's
PATH and are intended to be the official entry points:
invokeai-node-cli - new nodes-based CLI
invokeai-node-web - new nodes-based web server
invokeai - legacy CLI
invokeai-configure - install time configuration script
invokeai-merge - model merging script
invokeai-ti - textual inversion script
invokeai-model-install - model installer
invokeai-update - update script
invokeai-metadata" - retrieve JSON-formatted metadata from PNG files
protect invocations against black autoformatting
deps: upgrade to diffusers 0.14, safetensors 0.3, transformers 4.26, accelerate 0.16
Things to check for in this version:
- `diffusers` cache location is now more consistent with other
huggingface-hub using code (i.e. `transformers`) as of
https://github.com/huggingface/diffusers/pull/2005. I think ultimately
this should make @damian0815 (and other folks with multiple
diffusers-using projects) happier, but it's worth taking a look to make
sure the way @lstein set things up to respect `HF_HOME` is still
functioning as intended.
- I've gone ahead and updated `transformers` to the current version
(4.26), but I have a vague memory that we were holding it back at some
point? Need to look that up and see if that's the case and why.
This PR fixes the following scripts:
1) Scripts that can be executed within the repo's scripts directory.
Note that these are for development testing and are not intended
to be exposed to the user.
```
configure_invokeai.py - configuration
dream.py - the legacy CLI
images2prompt.py - legacy "dream prompt" retriever
invoke-new.py - new nodes-based CLI
invoke.py - the legacy CLI under another name
make_models_markdown_table.py - a utility used during the release/doc process
pypi_helper.py - another utility used during the release process
sd-metadata.py - retrieve JSON-formatted metadata from a PNG file
```
2) Scripts that are installed by pip install. They get placed into the
venv's
PATH and are intended to be the official entry points:
```
invokeai-node-cli - new nodes-based CLI
invokeai-node-web - new nodes-based web server
invokeai - legacy CLI
invokeai-configure - install time configuration script
invokeai-merge - model merging script
invokeai-ti - textual inversion script
invokeai-model-install - model installer
invokeai-update - update script
invokeai-metadata" - retrieve JSON-formatted metadata from PNG files
```
Fix error when using txt2img
ModuleNotFoundError: No module named 'invokeai.backend.models'
and
ModuleNotFoundError: No module named
'invokeai.backend.generator.diffusers_pipeline'
This PR fixes the following scripts:
1) Scripts that can be executed within the repo's scripts directory.
Note that these are for development testing and are not intended
to be exposed to the user.
configure_invokeai.py - configuration
dream.py - the legacy CLI
images2prompt.py - legacy "dream prompt" retriever
invoke-new.py - new nodes-based CLI
invoke.py - the legacy CLI under another name
make_models_markdown_table.py - a utility used during the release/doc process
pypi_helper.py - another utility used during the release process
sd-metadata.py - retrieve JSON-formatted metadata from a PNG file
2) Scripts that are installed by pip install. They get placed into the venv's
PATH and are intended to be the official entry points:
invokeai-node-cli - new nodes-based CLI
invokeai-node-web - new nodes-based web server
invokeai - legacy CLI
invokeai-configure - install time configuration script
invokeai-merge - model merging script
invokeai-ti - textual inversion script
invokeai-model-install - model installer
invokeai-update - update script
invokeai-metadata" - retrieve JSON-formatted metadata from PNG files
To avoid `git blame` recording all the autoformatting changes
under the name 'lstein', this PR adds a `.git-blame-ignore-revs`
that will ignore any provenance changes that occurred during the
recent refactor merge.
# All python code has been moved under `invokeai`. All vestiges of `ldm`
and `ldm.invoke` are now gone.
***You will need to run `pip install -e .` before the code will work
again!***
Everything seems to be functional, but extensive testing is advised.
A guide to where the files have gone is forthcoming.
This is the first phase of a big shifting of files and directories
in the source tree.
You will need to run `pip install -e .` before the code will work again!
Here's what's in the current commit:
1) Remove a lot of dead code that dealt with checkpoint and safetensor loading.
2) Entire ckpt_generator hierarchy is now gone!
3) ldm.invoke.generator.* => invokeai.generator.*
4) ldm.model.* => invokeai.model.*
5) ldm.invoke.model_manager => invokeai.model.model_manager
6) In addition, a number of frequently-accessed classes can be imported
from the invokeai.model and invokeai.generator modules:
from invokeai.generator import ( Generator, PipelineIntermediateState,
StableDiffusionGeneratorPipeline, infill_methods)
from invokeai.models import ( ModelManager, SDLegacyType
InvokeAIDiffuserComponent, AttentionMapSaver,
DDIMSampler, KSampler, PLMSSampler,
PostprocessingSettings )
* [nodes] Add better error handling to processor and CLI
* [nodes] Use more explicit name for marking node execution error
* [nodes] Update the processor call to error
This should make caching way easier and therefore speed up the image
(re-)creation a lot.
Other small improvements:
- reorder .dockerignore
- rename amd flavor to rocm to align with cuda flavor
- use `user:group` for definitions
- add `--platform=${TARGETPLATFORM}` to base
This PR adds the core of the node-based invocation system first
discussed in https://github.com/invoke-ai/InvokeAI/discussions/597 and
implements it through a basic CLI and API. This supersedes #1047, which
was too far behind to rebase.
## Architecture
### Invocations
The core of the new system is **invocations**, found in
`/ldm/invoke/app/invocations`. These represent individual nodes of
execution, each with inputs and outputs. Core invocations are already
implemented (`txt2img`, `img2img`, `upscale`, `face_restore`) as well as
a debug invocation (`show_image`). To implement a new invocation, all
that is required is to add a new implementation in this folder (there is
a markdown document describing the specifics, though it is slightly
out-of-date).
### Sessions
Invocations and links between them are maintained in a **session**.
These can be queued for invocation (either the next ready node, or all
nodes). Some notes:
* Sessions may be added to at any time (including after invocation), but
may not be modified.
* Links are always added with a node, and are always links from existing
nodes to the new node. These links can be relative "history" links, e.g.
`-1` to link from a previously executed node, and can link either
specific outputs, or can opportunistically link all matching outputs by
name and type by using `*`.
* There are no iteration/looping constructs. Most needs for this could
be solved by either duplicating nodes or cloning sessions. This is open
for discussion, but is a difficult problem to solve in a way that
doesn't make the code even more complex/confusing (especially regarding
node ids and history).
### Services
These make up the core the invocation system, found in
`/ldm/invoke/app/services`. One of the key design philosophies here is
that most components should be replaceable when possible. For example,
if someone wants to use cloud storage for their images, they should be
able to replace the image storage service easily.
The services are broken down as follows (several of these are
intentionally implemented with an initial simple/naïve approach):
* Invoker: Responsible for creating and executing **sessions** and
managing services used to do so.
* Session Manager: Manages session history. An on-disk implementation is
provided, which stores sessions as json files on disk, and caches
recently used sessions for quick access.
* Image Storage: Stores images of multiple types. An on-disk
implementation is provided, which stores images on disk and retains
recently used images in an in-memory cache.
* Invocation Queue: Used to queue invocations for execution. An
in-memory implementation is provided.
* Events: An event system, primarily used with socket.io to support
future web UI integration.
## Apps
Apps are available through the `/scripts/invoke-new.py` script (to-be
integrated/renamed).
### CLI
```
python scripts/invoke-new.py
```
Implements a simple CLI. The CLI creates a single session, and
automatically links all inputs to the previous node's output. Commands
are automatically generated from all invocations, with command options
being automatically generated from invocation inputs. Help is also
available for the cli and for each command, and is very verbose.
Additionally, the CLI supports command piping for single-line entry of
multiple commands. Example:
```
> txt2img --prompt "a cat eating sushi" --steps 20 --seed 1234 | upscale | show_image
```
### API
```
python scripts/invoke-new.py --api --host 0.0.0.0
```
Implements an API using FastAPI with Socket.io support for signaling.
API documentation is available at `http://localhost:9090/docs` or
`http://localhost:9090/redoc`. This includes OpenAPI schema for all
available invocations, session interaction APIs, and image APIs.
Socket.io signals are per-session, and can be subscribed to by session
id. These aren't currently auto-documented, though the code for event
emission is centralized in `/ldm/invoke/app/services/events.py`.
A very simple test html and script are available at
`http://localhost:9090/static/test.html` This demonstrates creating a
session from a graph, invoking it, and receiving signals from Socket.io.
## What's left?
* There are a number of features not currently covered by invocations. I
kept the set of invocations small during core development in order to
simplify refactoring as I went. Now that the invocation code has
stabilized, I'd love some help filling those out!
* There's no image metadata generated. It would be fairly
straightforward (and would make good sense) to serialize either a
session and node reference into an image, or the entire node into the
image. There are a lot of questions to answer around source images,
linked images, etc. though. This history is all stored in the session as
well, and with complex sessions, the metadata in an image may lose its
value. This needs some further discussion.
* We need a list of features (both current and future) that would be
difficult to implement without looping constructs so we can have a good
conversation around it. I'm really hoping we can avoid needing
looping/iteration in the graph execution, since it'll necessitate
separating an execution of a graph into its own concept/system, and will
further complicate the system.
* The API likely needs further filling out to support the UI. I think
using the new API for the current UI is possible, and potentially
interesting, since it could work like the new/demo CLI in a "single
operation at a time" workflow. I don't know how compatible that will be
with our UI goals though. It would be nice to support only a single API
though.
* Deeper separation of systems. I intentionally tried to not touch
Generate or other systems too much, but a lot could be gained by
breaking those apart. Even breaking apart Args into two pieces (command
line arguments and the parser for the current CLI) would make it easier
to maintain. This is probably in the future though.
author Kyle Schouviller <kyle0654@hotmail.com> 1669872800 -0800
committer Kyle Schouviller <kyle0654@hotmail.com> 1676240900 -0800
Adding base node architecture
Fix type annotation errors
Runs and generates, but breaks in saving session
Fix default model value setting. Fix deprecation warning.
Fixed node api
Adding markdown docs
Simplifying Generate construction in apps
[nodes] A few minor changes (#2510)
* Pin api-related requirements
* Remove confusing extra CORS origins list
* Adds response models for HTTP 200
[nodes] Adding graph_execution_state to soon replace session. Adding tests with pytest.
Minor typing fixes
[nodes] Fix some small output query hookups
[node] Fixing some additional typing issues
[nodes] Move and expand graph code. Add base item storage and sqlite implementation.
Update startup to match new code
[nodes] Add callbacks to item storage
[nodes] Adding an InvocationContext object to use for invocations to provide easier extensibility
[nodes] New execution model that handles iteration
[nodes] Fixing the CLI
[nodes] Adding a note to the CLI
[nodes] Split processing thread into separate service
[node] Add error message on node processing failure
Removing old files and duplicated packages
Adding python-multipart
- Add curated set of starter models based on team discussion. The final
list of starter models can be found in
`invokeai/configs/INITIAL_MODELS.yaml`
- To test model installation, I selected and installed all the models on
the list. This led to my discovering that when there are no more starter
models to display, the console front end crashes. So I made a fix to
this in which the entire starter model selection is no longer shown.
- Update model table in 050_INSTALL_MODELS.md
- Add guide to dealing with low-memory situations
- Version is now `v2.3.1`
- add new script `scripts/make_models_markdown_table.py` that parses
INITIAL_MODELS.yaml and creates markdown table for the model installation
documentation file
- update 050_INSTALLING_MODELS.md with above table, and add a warning
about additional license terms that apply to some of the models.
- Final list can be found in invokeai/configs/INITIAL_MODELS.yaml
- After installing all the models, I discovered a bug in the file
selection form that caused a crash when no remaining uninstalled
models remained. So had to fix this.
The sample_to_image method in `ldm.invoke.generator.base` was still
using ckpt-era code. As a result when the WebUI was set to show
"accurate" intermediate images, there'd be a crash. This PR corrects the
problem.
- Closes#2784
- Closes#2775
- Discord member @marcus.llewellyn reported that some civitai
2.1-derived checkpoints were not converting properly (probably
dreambooth-generated):
https://discord.com/channels/1020123559063990373/1078386197589655582/1078387806122025070
- @blessedcoolant tracked this down to a missing key that was used to
derive vector length of the CLIP model used by fetching the second
dimension of the tensor at "cond_stage_model.model.text_projection".
- On inspection, I found that the same second dimension can be recovered
from key 'cond_stage_model.model.ln_final.bias', and use that instead. I
hope this is correct; tested on multiple v1, v2 and inpainting models
and they converted correctly.
- While debugging this, I found and fixed several other issues:
- model download script was not pre-downloading the OpenCLIP
text_encoder or text_tokenizer. This is fixed.
- got rid of legacy code in `ckpt_to_diffuser.py` and replaced with
calls into `model_manager`
- more consistent status reporting in the CLI.
without this change, the project can be installed on 3.9 but not used
this also fixes the container images
Maybe we should re-enable Python 3.9 checks which would have prevented
this.
- Discord member @marcus.llewellyn reported that some civitai 2.1-derived checkpoints were
not converting properly (probably dreambooth-generated):
https://discord.com/channels/1020123559063990373/1078386197589655582/1078387806122025070
- @blessedcoolant tracked this down to a missing key that was used to
derive vector length of the CLIP model used by fetching the second
dimension of the tensor at "cond_stage_model.model.text_projection".
His proposed solution was to hardcode a value of 1024.
- On inspection, I found that the same second dimension can be
recovered from key 'cond_stage_model.model.ln_final.bias', and use
that instead. I hope this is correct; tested on multiple v1, v2 and
inpainting models and they converted correctly.
- While debugging this, I found and fixed several other issues:
- model download script was not pre-downloading the OpenCLIP
text_encoder or text_tokenizer. This is fixed.
- got rid of legacy code in `ckpt_to_diffuser.py` and replaced
with calls into `model_manager`
- more consistent status reporting in the CLI.
Root directory finding algorithm is:
2) use --root argument
2) use INVOKEAI_ROOT environment variable
3) use VIRTUAL_ENV environment variable
4) use ~/invokeai
Since developers are liable to put virtual environments in their
favorite places, not necessarily in the invokeai root directory, this PR
adds a sanity check that looks for the existence of
`VIRTUAL_ENV/invokeai.init`, and moves on to (4) if not found.
# This will constitute v2.3.1+rc2
## Windows installer enhancements
1. resize installer window to give more room for configure and download
forms
2. replace '\' with '/' in directory names to allow user to
drag-and-drop
folders into the dialogue boxes that accept directories.
3. similar change in CLI for the !import_model and !convert_model
commands
4. better error reporting when a model download fails due to network
errors
5. put the launcher scripts into a loop so that menu reappears after
invokeai, merge script, etc exits. User can quit with "Q".
6. do not try to download fp16 of sd-ft-mse-vae, since it doesn't exist.
7. cleaned up status reporting when installing models
8. Detect when install failed for some reason and print helpful error
message rather than stack trace.
9. Detect window size and resize to minimum acceptable values to provide
better display of configure and install forms.
10. Fix a bug in the CLI which prevented diffusers imported by their
repo_ids
from being correctly registered in the current session (though they
install
correctly)
11. Capitalize the "i" in Imported in the autogenerated descriptions.
Root directory finding algorithm is:
2) use --root argument
2) use INVOKEAI_ROOT environment variable
3) use VIRTUAL_ENV environment variable
4) use ~/invokeai
Since developer's are liable to put virtual environments in their
favorite places, not necessarily in the invokeai root directory, this
PR adds a sanity check that looks for the existence of
VIRTUAL_ENV/invokeai.init, and moves to (4) if not found.
- Fix a bug in the CLI which prevented diffusers imported by their repo_ids
from being correctly registered in the current session (though they install
correctly)
- Capitalize the "i" in Imported in the autogenerated descriptions.
1. resize installer window to give more room for configure and download forms
2. replace '\' with '/' in directory names to allow user to drag-and-drop
folders into the dialogue boxes that accept directories.
3. similar change in CLI for the !import_model and !convert_model commands
4. better error reporting when a model download fails due to network errors
5. put the launcher scripts into a loop so that menu reappears after
invokeai, merge script, etc exits. User can quit with "Q".
6. do not try to download fp16 of sd-ft-mse-vae, since it doesn't exist.
7. cleaned up status reporting when installing models
- Detect when install failed for some reason and print helpful error
message rather than stack trace.
- Detect window size and resize to minimum acceptable values to provide
better display of configure and install forms.
Currently translated at 81.4% (382 of 469 strings)
translationBot(ui): update translation (Russian)
Currently translated at 81.6% (382 of 468 strings)
Co-authored-by: Sergey Krashevich <svk@svk.su>
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/ru/
Translation: InvokeAI/Web UI
## Major Changes
The invokeai-configure script has now been refactored. The work of
selecting and downloading initial models at install time is now done by
a script named `invokeai-model-install` (module name is
`ldm.invoke.config.model_install`)
Screen 1 - adjust startup options:
Screen 2 - select SD models:
The calling arguments for `invokeai-configure` have not changed, so
nothing should break. After initializing the root directory, the script
calls `invokeai-model-install` to let the user select the starting
models to install.
`invokeai-model-install puts up a console GUI with checkboxes to
indicate which models to install. It respects the `--default_only` and
`--yes` arguments so that CI will continue to work. Here are the various
effects you can achieve:
`invokeai-configure`
This will use console-based UI to initialize invokeai.init,
download support models, and choose and download SD models
`invokeai-configure --yes`
Without activating the GUI, populate invokeai.init with default values,
download support models and download the "recommended" SD models
`invokeai-configure --default_only`
Activate the GUI for changing init options, but don't show the SD
download
form, and automatically download the default SD model (currently SD-1.5)
`invokeai-model-install`
Select and install models. This can be used to download arbitrary
models from the Internet, install HuggingFace models using their
repo_id,
or watch a directory for models to load at startup time
`invokeai-model-install --yes`
Import the recommended SD models without a GUI
`invokeai-model-install --default_only`
As above, but only import the default model
## Flexible Model Imports
The console GUI allows the user to import arbitrary models into InvokeAI
using:
1. A HuggingFace Repo_id
2. A URL (http/https/ftp) that points to a checkpoint or safetensors
file
3. A local path on disk pointing to a checkpoint/safetensors file or
diffusers directory
4. A directory to be scanned for all checkpoint/safetensors files to be
imported
The UI allows the user to specify multiple models to bulk import. The
user can specify whether to import the ckpt/safetensors as-is, or
convert to `diffusers`. The user can also designate a directory to be
scanned at startup time for checkpoint/safetensors files.
## Backend Changes
To support the model selection GUI PR introduces a new method in
`ldm.invoke.model_manager` called `heuristic_import(). This accepts a
string-like object which can be a repo_id, URL, local path or directory.
It will figure out what the object is and import it. It interrogates the
contents of checkpoint and safetensors files to determine what type of
SD model they are -- v1.x, v2.x or v1.x inpainting.
## Installer
I am attaching a zip file of the installer if you would like to try the
process from end to end.
[InvokeAI-installer-v2.3.0.zip](https://github.com/invoke-ai/InvokeAI/files/10785474/InvokeAI-installer-v2.3.0.zip)
motivation: i want to be doing future prompting development work in the
`compel` lib (https://github.com/damian0815/compel) - which is currently
pip installable with `pip install compel`.
-At some point pathlib was added to the list of imported modules and
this broken the os.path code that assembled the sample data set.
-Now fixed by replacing os.path calls with Path methods
-At some point pathlib was added to the list of imported modules and this
broken the os.path code that assembled the sample data set.
-Now fixed by replacing os.path calls with Path methods
- Disable responsive resizing below starting dimensions (you can make
form larger, but not smaller than what it was at startup)
- Fix bug that caused multiple --ckpt_convert entries (and similar) to
be written to init file.
This bug is related to the format in which we stored prompts for some time: an array of weighted subprompts.
This caused some strife when recalling a prompt if the prompt had colons in it, due to our recently introduced handling of negative prompts.
Currently there is no need to store a prompt as anything other than a string, so we revert to doing that.
Compatibility with structured prompts is maintained via helper hook.
Lots of earlier embeds use a common trigger token such as * or the
hebrew letter shan. Previously, the textual inversion manager would
refuse to load the second and subsequent embeddings that used a
previously-claimed trigger. Now, when this case is encountered, the
trigger token is replaced by <filename> and the user is informed of the
fact.
1. Fixed display crash when the number of installed models is less than
the number of desired columns to display them.
2. Added --ckpt_convert option to init file.
Enhancements:
1. Directory-based imports will not attempt to import components of diffusers models.
2. Diffuser directory imports now supported
3. Files that end with .ckpt that are not Stable Diffusion models (such as VAEs) are
skipped during import.
Bugs identified in Psychedelicious's review:
1. The invokeai-configure form now tracks the current contents of `invokeai.init` correctly.
2. The autoencoders are no longer treated like installable models, but instead are
mandatory support models. They will no longer appear in `models.yaml`
Bugs identified in Damian's review:
1. If invokeai-model-install is started before the root directory is initialized, it will
call invokeai-configure to fix the matter.
2. Fix bug that was causing empty `models.yaml` under certain conditions.
3. Made import textbox smaller
4. Hide the "convert to diffusers" options if nothing to import.
In theory, this reduces peak memory consumption by doing the conditioned
and un-conditioned predictions one after the other instead of in a
single mini-batch.
In practice, it doesn't reduce the reported "Max VRAM used for this
generation" for me, even without xformers. (But it does slow things down
by a good 18%.)
That suggests to me that the peak memory usage is during VAE decoding,
not the diffusion unet, but ymmv. It does [improve things for gogurt's
16 GB
M1](https://github.com/invoke-ai/InvokeAI/pull/2732#issuecomment-1436187407),
so it seems worthwhile.
To try it out, use the `--sequential_guidance` option:
2dded68267/ldm/invoke/args.py (L487-L492)
- Adds an update action to launcher script
- This action calls new python script `invokeai-update`, which prompts
user to update to latest release version, main development version, or
an arbitrary git tag or branch name.
- It then uses `pip` to update to whatever tag was specified.
The user interface (such as it is) looks like this:
- The TI script was looping over all files in the training image
directory, regardless of whether they were image files or not. This PR
adds a check for image file extensions.
-
- Closes#2715
- Fixes longstanding bug in the token vector size code which caused .pt
files to be assigned the wrong token vector length. These were then
tossed out during directory scanning.
- Fixes longstanding bug in the token vector size code which caused
.pt files to be assigned the wrong token vector length. These
were then tossed out during directory scanning.
- Fixed the test for token length; tested on several .pt and .bin files
- Also added a __main__ entrypoint for CLI.py, to make pdb debugging a
bit more convenient.
When selecting the last model of the third model-list in the
model-merging-TUI it crashed because the code forgot about the "None"
element.
Additionally it seems that it accidentally always took the wrong model
as third model if selected?
This simple fix resolves both issues.
Added symmetry to Invoke based on discussions with @damian0815. This can currently only be activated via the CLI with the `--h_symmetry_time_pct` and `--v_symmetry_time_pct` options. Those take values from 0.0-1.0, exclusive, indicating the percentage through generation at which symmetry is applied as a one-time operation. To have symmetry in either axis applied after the first step, use a very low value like 0.001.
- not sure why, but at some pont --ckpt_convert (which converts legacy checkpoints)
into diffusers in memory, stopped working due to float16/float32 issues.
- this commit repairs the problem
- also removed some debugging messages I found in passing
- Fixed the test for token length; tested on several .pt and .bin files
- Also added a __main__ entrypoint for CLI.py, to make pdb debugging a bit
more convenient.
- You can now achieve several effects:
`invokeai-configure`
This will use console-based UI to initialize invokeai.init,
download support models, and choose and download SD models
`invokeai-configure --yes`
Without activating the GUI, populate invokeai.init with default values,
download support models and download the "recommended" SD models
`invokeai-configure --default_only`
As above, but only download the default SD model (currently SD-1.5)
`invokeai-model-install`
Select and install models. This can be used to download arbitrary
models from the Internet, install HuggingFace models using their repo_id,
or watch a directory for models to load at startup time
`invokeai-model-install --yes`
Import the recommended SD models without a GUI
`invokeai-model-install --default_only`
As above, but only import the default model
A few bugs fixed.
- After the recent update to the Cancel Button, it was no longer
respecting sizing in Floating Mode and the Beta Canvas. Fixed that.
- After the recent dependency update, useHotkeys was bugging out for the
fullscreen hotkey `f`. Realized this was happening because the hotkey
was initialized in two places -- in both the gallery and the parameter
floating button. Removed it from both those places and moved it to the
InvokeTabs component. It makes sense to reside it here because it is a
global hotkey.
- Also added index `0` to the default Accordion index in state in order
to ensure that the main accordions stay open. Conveniently this works
great on all tabs. We have all the primary options in accordions so they
stay open. And as for advanced settings, the first one is always Seed
which is an important accordion, so it opens up by default.
Think there may be some more bugs. Looking in to them.
After upgrading the deps, the full screen hotkey started to bug out. I believe this was happening because it was triggered in two different components causing it to run twice. Removed it from both floating buttons and moved it to the Invoke tab. Makes sense to keep it there as it is a global hotkey.
After the recent changes the Cancel button wasn't maintaining min height in floating mode. Also the new button group was not scaling in width correctly on the Canvas Beta UI. Fixed both.
- Adds a translation status badge
- Adds a blurb about contributing a translation (we want Weblate to be
the source of truth for translations, and to avoid updating translations
directly here)
- Upgraded all dependencies
- Removed beta TS 5.0 as it conflicted with some packages
- Added types for `Array.prototype.findLast` and
`Array.prototype.findLastIndex` (these definitions are provided in TS
5.0
- Fixed fixed type import syntax in a few components
- Re-patched `redux-deep-persist` and tested to ensure the patch still
works
The husky pre-commit command was `npx run lint`, but it should run
`lint-staged`. Also, `npx` wasn't working for me. Changed the command to
`npm run lint-staged` and it all works. Extended the `lint-staged`
triggers to hit `json`, `scss` and `html`.
When encountering a bad embedding, InvokeAI was asking about reconfiguring models. This is because the embedding load error was never handled - it now is.
- Upgraded all dependencies
- Removed beta TS 5.0 as it conflicted with some packages
- Added types for `Array.prototype.findLast` and `Array.prototype.findLastIndex` (these definitions are provided in TS 5.0
- Fixed fixed type import syntax in a few components
- Re-patched `redux-deep-persist` and tested to ensure the patch still works
Model Manager lags a bit if you have a lot of models.
Basically added a fake delay to rendering the model list so the modal
has time to load first. Hacky but if it works it works.
## What was the problem/requirement? (What/Why)
Frequently, I wish to cancel the processing of images, but also want the
current image to finalize before I do. To work around this, I need to
wait until the current one finishes before pressing the cancel.
## What was the solution? (How)
* Implemented a button that allows to "Cancel after current iteration,"
which stores a state in the UI that will attempt to cancel the
processing after the current image finishes
* If the button is pressed again, while it is spinning and before the
next iteration happens, this will stop the scheduling of the cancel, and
behave as if the button was never pressed.
### Minor
* Added `.yarn` to `.gitignore` as this was an output folder produced
from following Frontend's README
### Revision 2
#### Major
* Changed from a standalone button to a context menu next to the
original cancel button. Pressing the context menu will give the
drop-down option to select which type of cancel method the user prefers,
and they can press that button for canceling in the specified type
* Moved states to system state for cross-screen and toggled cancel types
management
* Added in distribution for the target yarn version (allowing any
version of yarn to compile successfully), and updated the README to
ensure `--immutable` is passed for onboarding developers
#### Minor
* Updated `.gitignore` to ignore specific yarn folders, as specified by
their team -
https://yarnpkg.com/getting-started/qa#which-files-should-be-gitignored
## How were these changes tested?
* `yarn dev` => Server started successfully
* Manual testing on the development server to ensure the button behaved
as expected
* `yarn run build` => Success
### Artifacts
#### Revision 1
* Video showing the UI changes in action
https://user-images.githubusercontent.com/89283782/218347722-3a15ce61-2d8c-4c38-b681-e7a3e79dd595.mov
* Images showing the basic UI changes
#### Revision 2
* Video showing the UI changes in action
https://user-images.githubusercontent.com/89283782/219901217-048d2912-9b61-4415-85fd-9e8fedb00c79.mov
* Images showing the basic UI changes
(Default state)
(Drop-down context menu active)
(Scheduled cancel selected and running)
(Scheduled cancel started)
## Notes
* Using `SystemState`'s `currentStatus` variable, when the value is
`common:statusIterationComplete` is an alternative to this approach (and
would be more optimal as it should prevent the next iteration from even
starting), but since the names are within the translations, rather than
an enum or other type, this method of tracking the current iteration was
used instead.
* `isLoading` on `IAIIconButton` caused the Icon Button to also be
disabled, so the current solution works around that with conditionally
rendering the icon of the button instead of passing that value.
* I don't have context on the development expectation for `dist` folder
interactions (and couldn't find any documentation outside of the
`.gitignore` mentioning that the folder should remain. Let me know if
they need to be modified a certain way.
- The checkpoint conversion script was generating diffusers models with
the safety checker set to null. This resulted in models that could not
be merged with ones that have the safety checker activated.
- This PR fixes the issue by incorporating the safety checker into all
1.x-derived checkpoints, regardless of user's nsfw_checker setting.
- The checkpoint conversion script was generating diffusers models
with the safety checker set to null. This resulted in models
that could not be merged with ones that have the safety checker
activated.
- This PR fixes the issue by incorporating the safety checker into
all 1.x-derived checkpoints, regardless of user's nsfw_checker setting.
Also tighten up the typing of `device` attributes in general.
Fixes
> ValueError: Expected a torch.device with a specified index or an
integer, but got:cuda
Weblate's first PR was it attempting to fix some translation issues we
had overlooked!
It wanted to remove some keys which it did not see in our translation
source due to typos.
This PR instead corrects the key names to resolve the issues.
# Weblate Translation
After doing a full integration test of 3 translation service providers
on my fork of InvokeAI, we have chosen
[Weblate](https://hosted.weblate.org). The other two viable options were
[Crowdin](https://crowdin.com/) and
[Transifex](https://www.transifex.com/).
Weblate was the choice because its hosted service provides a very solid
UX / DX, can scale as much as we may ever need, is FOSS itself, and
generously offers free hosted service to other libre projects like ours.
## How it works
Weblate hosts its own fork of our repo and establishes a kind of
unidirectional relationship between our repo and its fork.
### InvokeAI --> Weblate
The `invoke-ai/InvokeAI` repo has had the Weblate GitHub app added to
it. This app watches for changes to our translation source
(`invokeai/frontend/public/locales/en.json`) and then updates the
Weblate fork. The Weblate UI then knows there are new strings to be
translated, or changes to be made.
### Translation
Our translators can then update the translations on the Weblate UI. The
plan now is to invite individual community members who have expressed
interest in maintaining a language or two and give them access to the
app. We can also open the doors to the general public if desired.
### Weblate --> InvokeAI
When a translation is ready or changed, the system will make a PR to
`main`. We have a substantial degree of control over this and will
likely manually trigger these PRs instead of letting them fire off
automatically.
Once a PR is merged, we will still need to rebuild the web UI. I think
we can set things up so that we only need the rebuild when a totally new
language is added, but for now, we will stick to this relatively simple
setup.
## This PR
This PR sets up the web UI's translation stuff to work with Weblate:
- merged each locale into a single file
- updated the i18next config and UI to work with this simpler file
structure
- update our eslint and prettier rules to ensure the locale files have
the same format as what Weblate outputs (`tabWidth: 4`)
- added a thank you to Weblate in our README
Once this is merged, I'll link Weblate to `main` and do a couple tests
to ensure it is all working as expected.
This fixes a few cosmetic bugs in the merge models console GUI:
1) Fix the minimum and maximum ranges on alpha. Was 0.05 to 0.95. Now
0.01 to 0.99.
2) Don't show the 'add_difference' interpolation method when 2 models
selected, or the other three methods when three models selected
## Convert v2 models in CLI
- This PR introduces a CLI prompt for the proper configuration file to
use when converting a ckpt file, in order to support both inpainting
and v2 models files.
- When user tries to directly !import a v2 model, it prints out a proper
warning that v2 ckpts are not directly supported and converts it into a
diffusers model automatically.
The user interaction looks like this:
```
(stable-diffusion-1.5) invoke> !import_model /home/lstein/graphic-art.ckpt
Short name for this model [graphic-art]: graphic-art-test
Description for this model [Imported model graphic-art]: Imported model graphic-art
What type of model is this?:
[1] A model based on Stable Diffusion 1.X
[2] A model based on Stable Diffusion 2.X
[3] An inpainting model based on Stable Diffusion 1.X
[4] Something else
Your choice: [1] 2
```
In addition, this PR enhances the bulk checkpoint import function. If a
directory path is passed to `!import_model` then it will be scanned for
`.ckpt` and `.safetensors` files. The user will be prompted to import
all the files found, or select which ones to import.
Addresses
https://discord.com/channels/1020123559063990373/1073730061380894740/1073954728544845855
- fix alpha slider to show values from 0.01 to 0.99
- fix interpolation list to show 'difference' method for 3 models,
- and weighted_sum, sigmoid and inverse_sigmoid methods for 2
Porting over as many usable options to slider as possible.
- Ported Face Restoration settings to Sliders.
- Ported Upscale Settings to Sliders.
- Ported Variation Amount to Sliders.
- Ported Noise Threshold to Sliders <-- Optimized slider so the values
actually make sense.
- Ported Perlin Noise to Sliders.
- Added a suboption hook for the High Res Strength Slider.
- Fixed a couple of small issues with the Slider component.
- Ported Main Options to Sliders.
- Corrected error that caused --full-precision argument to be ignored
when models downloaded using the --yes argument.
- Improved autodetection of v1 inpainting files; no longer relies on the
file having 'inpaint' in the name.
* new OffloadingDevice loads one model at a time, on demand
* fixup! new OffloadingDevice loads one model at a time, on demand
* fix(prompt_to_embeddings): call the text encoder directly instead of its forward method
allowing any associated hooks to run with it.
* more attempts to get things on the right device from the offloader
* more attempts to get things on the right device from the offloader
* make offloading methods an explicit part of the pipeline interface
* inlining some calls where device is only used once
* ensure model group is ready after pipeline.to is called
* fixup! Strategize slicing based on free [V]RAM (#2572)
* doc(offloading): docstrings for offloading.ModelGroup
* doc(offloading): docstrings for offloading-related pipeline methods
* refactor(offloading): s/SimpleModelGroup/FullyLoadedModelGroup
* refactor(offloading): s/HotSeatModelGroup/LazilyLoadedModelGroup
to frame it is the same terms as "FullyLoadedModelGroup"
---------
Co-authored-by: Damian Stewart <null@damianstewart.com>
- filter paths for `build-container.yml` and `test-invoke-pip.yml`
- add workflow to pass required checks on PRs with `paths-ignore`
- this triggers if `test-invoke-pip.yml` does not
- fix "CI checks on main link" in `/README.md`
- filter paths for `build-container.yml` and `test-invoke-pip.yml`
- add workflow to pass required checks on PRs with `paths-ignore`
- this triggers if `test-invoke-pip.yml` does not
- fix "CI checks on main link" in `/README.md`
Assuming that mixing `"literal strings"` and `{'JSX expressions'}`
throughout the code is not for a explicit reason but just a result IDE
autocompletion, I changed all props to be consistent with the
conventional style of using simple string literals where it is
sufficient.
This is a somewhat trivial change, but it makes the code a little more
readable and uniform
- quashed multiple bugs in model conversion and importing
- found old issue in handling of resume of interrupted downloads
- will require extensive testing
### WebUI Model Conversion
**Model Search Updates**
- Model Search now has a radio group that allows users to pick the type
of model they are importing. If they know their model has a custom
config file, they can assign it right here. Based on their pick, the
model config data is automatically populated. And this same information
is used when converting the model to `diffusers`.
- Files named `model.safetensors` and
`diffusion_pytorch_model.safetensors` are excluded from the search
because these are naming conventions used by diffusers models and they
will end up showing on the list because our conversion saves safetensors
and not bin files.
**Model Conversion UI**
- The **Convert To Diffusers** button can be found on the Edit page of
any **Checkpoint Model**.
- When converting the model, the entire process is handled
automatically. The corresponding config while at the time of the Ckpt
addition is used in the process.
- Users are presented with the choice on where to save the diffusers
converted model - same location as the ckpt, InvokeAI models root folder
or a completely custom location.
- When the model is converted, the checkpoint entry is replaced with the
diffusers model entry. A user can readd the ckpt if they wish to.
---
More or less done. Might make some minor UX improvements as I refine
things.
Tensors with diffusers no longer have to be multiples of 8. This broke Perlin noise generation. We now generate noise for the next largest multiple of 8 and return a cropped result. Fixes#2674.
`generator` now asks `InvokeAIDiffuserComponent` to do postprocessing work on latents after every step. Thresholding - now implemented as replacing latents outside of the threshold with random noise - is called at this point. This postprocessing step is also where we can hook up symmetry and other image latent manipulations in the future.
Note: code at this layer doesn't need to worry about MPS as relevant torch functions are wrapped and made MPS-safe by `generator.py`.
1. Now works with sites that produce lots of redirects, such as CIVITAI
2. Derive name of destination model file from HTTP Content-Disposition header,
if present.
3. Swap \\ for / in file paths provided by users, to hopefully fix issues with
Windows.
This PR adds a new attributer to ldm.generate, `embedding_trigger_strings`:
```
gen = Generate(...)
strings = gen.embedding_trigger_strings
strings = gen.embedding_trigger_strings()
```
The trigger strings will change when the model is updated to show only
those strings which are compatible with the current
model. Dynamically-downloaded triggers from the HF Concepts Library
will only show up after they are used for the first time. However, the
full list of concepts available for download can be retrieved
programatically like this:
```
from ldm.invoke.concepts_lib import HuggingFAceConceptsLibrary
concepts = HuggingFaceConceptsLibrary()
trigger_strings = concepts.list_concepts()
```
I have added the arabic locale files. There need to be some
modifications to the code in order to detect the language direction and
add it to the current document body properties.
For example we can use this:
import { appWithTranslation, useTranslation } from "next-i18next";
import React, { useEffect } from "react";
const { t, i18n } = useTranslation();
const direction = i18n.dir();
useEffect(() => {
document.body.dir = direction;
}, [direction]);
This should be added to the app file. It uses next-i18next to
automatically get the current language and sets the body text direction
(ltr or rtl) depending on the selected language.
## Provide informative error messages when TI and Merge scripts have
insufficient space for console UI
- The invokeai-ti and invokeai-merge scripts will crash if there is not
enough space in the console to fit the user interface (even after
responsive formatting).
- This PR intercepts the errors and prints a useful error message
advising user to make window larger.
1. The invokeai-configure script has now been refactored. The work of
selecting and downloading initial models at install time is now done
by a script named invokeai-initial-models (module
name is ldm.invoke.config.initial_model_select)
The calling arguments for invokeai-configure have not changed, so
nothing should break. After initializing the root directory, the
script calls invokeai-initial-models to let the user select the
starting models to install.
2. invokeai-initial-models puts up a console GUI with checkboxes to
indicate which models to install. It respects the --default_only
and --yes arguments so that CI will continue to work.
3. User can now edit the VAE assigned to diffusers models in the CLI.
4. Fixed a bug that caused a crash during model loading when the VAE
is set to None, rather than being empty.
- The invokeai-ti and invokeai-merge scripts will crash if there is not enough space
in the console to fit the user interface (even after responsive formatting).
- This PR intercepts the errors and prints a useful error message advising user to
make window larger.
- fix unused variables and f-strings found by pyflakes
- use global_converted_ckpts_dir() to find location of diffusers
- fixed bug in model_manager that was causing the description of converted
models to read "Optimized version of {model_name}'
Strategize slicing based on free [V]RAM when not using xformers. Free [V]RAM is evaluated at every generation. When there's enough memory, the entire generation occurs without slicing. If there is not enough free memory, we use diffusers' sliced attention.
- Adds an update action to launcher script
- This action calls new python script `invokeai-update`, which prompts
user to update to latest release version, main development version,
or an arbitrary git tag or branch name.
- It then uses `pip` to update to whatever tag was specified.
Some of the core features of this PR include:
- optional push image to dockerhub (will be skipped in repos which
didn't set it up)
- stop using the root user at runtime
- trigger builds also for update/docker/* and update/ci/docker/*
- always cache image from current branch and main branch
- separate caches for container flavors
- updated comments with instructions in build.sh and run.sh
This commit cleans up the code that did bulk imports of legacy model
files. The code has been refactored, and the user is now offered the
option of importing all the model files found in the directory, or
selecting which ones to import.
Users can now pick the folder to save their diffusers converted model. It can either be the same folder as the ckpt, or the invoke root models folder or a totally custom location.
Fixed a couple of bugs:
1. The original config file for the ckpt file is derived from the entry in
`models.yaml` rather than relying on the user to select. The implication
of this is that V2 ckpt models need to be assigned `v2-inference-v.yaml`
when they are first imported. Otherwise they won't convert right. Note
that currently V2 ckpts are imported with `v1-inference.yaml`, which
isn't right either.
2. Fixed a backslash in the output diffusers path, which was causing
load failures on Linux.
Remaining issues:
1. The radio buttons for selecting the model type are
nonfunctional. It feels to me like these should be moved into the
dialogue for importing ckpt/safetensors files, because this is
where the algorithm needs help from the user.
2. The output diffusers model is written into the same directory as
the input ckpt file. The CLI does it differently and stores the
diffusers model in `ROOTDIR/models/converted-ckpts`. We should
settle on one way or the other.
Converted the picker options to a Radio Group and also updated the backend to use the appropriate config if it is a v2 model that needs to be converted.
- This PR introduces a CLI prompt for the proper configuration file to
use when converting a ckpt file, in order to support both inpainting
and v2 models files.
- When user tries to directly !import a v2 model, it prints out a proper
warning that v2 ckpts are not directly supported.
## What was the problem/requirement? (What/Why)
* Windows location for the Python environment activate location is
currently incorrect
* Due to this, this command will fail for Windows-based users
* The contributing link within the `Developer Install` sections leads to
a [404](https://invoke-ai.github.io/index.md#Contributing)
* `Developer Install`'s numbered list currently lists 1, 1, 2, . . .
## What was the solution? (How)
* Changed the location of Windows script based on actual location -
[reference](https://docs.python.org/3/library/venv.html)
* Moved the link to point to one directory higher -- the main index.md
* Minor format adjustments to allow for the numbered list to appear as
expected
## How were these changes tested?
* `mkdocs serve` => Verified on local server that the changes reflected
as expected
## Notes
Contributing mentions to set the upstream towards the `development`
branch, but that branch has been untouched for several months, so I've
pointed to the `main` branch. Let me know if we need to switch to a
different one.
…odels
- If CLI asked to convert the currently loaded model, the model would
crash on the first rendering. CLI will now refuse to convert a model
loaded in memory (probably a good idea in any case).
- CLI will offer the `v1-inpainting-inference.yaml` as the configuration
file when importing an inpainting a .ckpt or .safetensors file that has
"inpainting" in the name. Otherwise it offers `v1-inference.yaml` as the
default.
rather than bypassing any path with diffusers in it, im specifically bypassing model.safetensors and diffusion_pytorch_model.safetensors both of which should be diffusers files in most cases.
- If CLI asked to convert the currently loaded model, the model would crash
on the first rendering. CLI will now refuse to convert a model loaded
in memory (probably a good idea in any case).
- CLI will offer the `v1-inpainting-inference.yaml` as the configuration
file when importing an inpainting a .ckpt or .safetensors file that
has "inpainting" in the name. Otherwise it offers `v1-inference.yaml`
as the default.
Found a couple of places where the formatting was messed up. I also
added a "Quick Start Guide" to the README for people who encounter
InvokeAI through PyPi. It features the PyPi install!
pulling in denoising support from upstream (its already there, invoke
just isn't using it). I've enabled this as a command line argument as
construction of the ESRGAN handler happens once. Ideally this would be a
UI option that could be adjusted for each upscaling task. Unfortunately
that is beyond my current level of InvokeAI-foo.
Upstream reference is here, starting on line 99 "use dni to control the
denoise strength"
https://github.com/xinntao/Real-ESRGAN/blob/master/inference_realesrgan.py
- This makes the launcher options menu on Windows look and act the same
as the Linux/Mac launcher, which previously was lacking the command-line
help option and didn't list item (6) as an option.
Work in progress. I am reviewing and updating the documentation for
2.3.0. The following sections need to be done:
- [x] index.md
- [x] installation/010_INSTALL_AUTOMATED.md
- [x] installation/020_INSTALL_MANUAL.md
- [x] installation/030_INSTALL_CUDA_AND_ROCM.md (needs to be written
from scratch)
- [x] installation/040_INSTALL_DOCKER.md
- [x] installation/050_INSTALLING_MODELS.md
- [x] features/CLI.md
- [x] features/WEB.md
Using Windows 10 I found I needed to use double backslashes to import a
new model, when using single backslash the output would say
"e:_ProjectsCodemodelsldmstable-diffusion-model-to-import.ckpt is
neither the path to a .ckpt file nor a diffusers repository id. Can't
import." This added tip in the documentation will help Windows users
overcome this.
- The following were supposed to be equivalent, but the latter crashes:
```
invoke> banana sushi
invoke> --prompt="banana sushi"
```
This PR fixes the problem.
- Fixes#2548
- This makes the launcher options menu on Windows look and act the same
as the Linux/Mac launcher, which previously was lacking the command-line
help option and didn't list item (6) as an option.
The `useHotkeys` hook for this hotkey didn't have `isConnected` or `isProcessing` in its dependencies array. This prevented `handleDelete()` from dispatching the delete request.
This is an early draft of a codeowners file for InvokeAI. It has plenty
of gaps in it. Please use this PR to add yourself and others where
appropriate.
- The following were supposed to be equivalent, but the latter crashes:
```
invoke> banana sushi
invoke> --prompt="banana sushi"
```
This PR fixes the problem.
- Fixes#2548
This adds some platform-specific help messages to the installer welcome
screen:
- For Windows, the message encourages them to install VC++ core
libraries and the registry long name patch
- For MacOSX, the message warns the user to install the XCode tools.
I found I needed to use double backslashes to import a new model, when using single backslash the output would say "e:_ProjectsCodemodelsldmstable-diffusion-model-to-import.ckpt is neither the path to a .ckpt file nor a diffusers repository id. Can't import." This added tip in the documentation will help Windows users overcome this.
- `eslint` and `prettier` configs
- `husky` to format and lint via pre-commit hook
- `babel-plugin-transform-imports` to treeshake `lodash` and other packages if needed
Lints and formats codebase.
`options` slice was huge and managed a mix of generation parameters and general app settings. It has been split up:
- Generation parameters are now in `generationSlice`.
- Postprocessing parameters are now in `postprocessingSlice`
- UI related things are now in `uiSlice`
There is probably more to be done, like `gallerySlice` perhaps should only manage internal gallery state, and not if the gallery is displayed.
Full-slice selectors have been made for each slice.
Other organisational tweaks.
Previously conversions of .ckpt and .safetensors files to diffusers
models were failing with channel mismatch errors. This is corrected
with this PR.
- The model_manager convert_and_import() method now accepts the path
to the checkpoint file's configuration file, using the parameter
`original_config_file`. For inpainting files this should be set to
the full path to `v1-inpainting-inference.yaml`.
- If no configuration file is provided in the call, then the presence
of an inpainting file will be inferred at the
`ldm.ckpt_to_diffuser.convert_ckpt_to_diffUser()` level by looking
for the string "inpaint" in the path. AUTO1111 does something
similar to this, but it is brittle and not recommended.
- This PR also changes the model manager model_names() method to return
the model names in case folded sort order.
- `eslint` and `prettier` configs
- `husky` to format and lint via pre-commit hook
- `babel-plugin-transform-imports` to treeshake `lodash` and other packages if needed
Lints and formats codebase.
`options` slice was huge and managed a mix of generation parameters and general app settings. It has been split up:
- Generation parameters are now in `generationSlice`.
- Postprocessing parameters are now in `postprocessingSlice`
- UI related things are now in `uiSlice`
There is probably more to be done, like `gallerySlice` perhaps should only manage internal gallery state, and not if the gallery is displayed.
Full-slice selectors have been made for each slice.
Other organisational tweaks.
# enhance model_manager support for converting inpainting ckpt files
Previously conversions of .ckpt and .safetensors files to diffusers
models were failing with channel mismatch errors. This is corrected
with this PR.
- The model_manager convert_and_import() method now accepts the path
to the checkpoint file's configuration file, using the parameter
`original_config_file`. For inpainting files this should be set to
the full path to `v1-inpainting-inference.yaml`.
- If no configuration file is provided in the call, then the presence
of an inpainting file will be inferred at the
`ldm.ckpt_to_diffuser.convert_ckpt_to_diffUser()` level by looking
for the string "inpaint" in the path. AUTO1111 does something
similar to this, but it is brittle and not recommended.
- This PR also changes the model manager model_names() method to return
the model names in case folded sort order.
- Diffusers Sampler list is independent from CKPT Sampler list. And the
app will load the correct list based on what model you have loaded.
- Isolated the activeModelSelector coz this is used in multiple places.
- Possible fix to the white screen bug that some users face. This was
happening because of a possible null in the active model list
description tag. Which should hopefully now be fixed with the new
activeModelSelector.
I'll keep tabs on the last thing. Good to go.
For the torch and torchvision libraries **only**, the installer will now
pass the pip `--force-reinstall` option. This is intended to fix issues
with the user getting a CPU-only version of torch and then not being
able to replace it.
Previously conversions of .ckpt and .safetensors files to diffusers
models were failing with channel mismatch errors. This is corrected
with this PR.
- The model_manager convert_and_import() method now accepts the path
to the checkpoint file's configuration file, using the parameter
`original_config_file`. For inpainting files this should be set to
the full path to `v1-inpainting-inference.yaml`.
- If no configuration file is provided in the call, then the presence
of an inpainting file will be inferred at the
`ldm.ckpt_to_diffuser.convert_ckpt_to_diffUser()` level by looking
for the string "inpaint" in the path. AUTO1111 does something
similar to this, but it is brittle and not recommended.
- This PR also changes the model manager model_names() method to return
the model names in case folded sort order.
test-invoke-pip.yml:
- enable caching of pip dependencies in `actions/setup-python@v4`
- add workflow_dispatch trigger
- fix indentation in concurrency
- set env `PIP_USE_PEP517: '1'`
- cache python dependencies
- remove models cache (since we currently use 190.96 GB of 10 GB while I
am writing this)
- add step to set `INVOKEAI_OUTDIR`
- add outdir arg to invokeai
- fix path in archive results
model_manager.py:
- read files in chunks when calculating sha (windows runner is crashing
otherwise)
- help users to avoid glossing over per-platform prerequisites
- better link colouring
- update link to community instructions to install xcode command line tools
- Issue is that if insufficient diffusers models are defined in
models.yaml the frontend would ungraciously crash.
- Now it emits appropriate error messages telling user what the problem
is.
- Issue is that if insufficient diffusers models are defined in
models.yaml the frontend would ungraciously crash.
- Now it emits appropriate error messages telling user what the problem
is.
- dont build frontend since complications with QEMU
- set pip cache dir
- add pip cache to all pip related build steps
- dont lock pip cache
- update dockerignore to exclude uneeded files
env.sh:
- move check for torch to CONVTAINER_FLAVOR detection
Dockerfile
- only mount `/var/cache/apt` for apt related steps
- remove `docker-clean` from `/etc/apt/apt.conf.d` for BuildKit cache
- remove apt-get clean for BuildKit cache
- only copy frontend to frontend-builder
- mount `/usr/local/share/.cache/yarn` in frountend-builder
- separate steps for yarn install and yarn build
- build pytorch in pyproject-builder
build.sh
- prepare for installation with extras
This change allows passing a directory with multiple models in it to be
imported.
Ensures that diffusers directories will still work.
Fixed up some minor type issues.
This allows the --log_tokenization option to be used as a command line
argument (or from invokeai.init), making it possible to view
tokenization information in the terminal when using the web interface.
- This fixes an edge case crash when the textual inversion frontend
tried to display the list of models and no default model defined
in models.yaml
Co-authored-by: Jonathan <34005131+JPPhoto@users.noreply.github.com>
This allows the --log_tokenization option to be used as a command line argument (or from invokeai.init), making it possible to view tokenization information in the terminal when using the web interface.
- Rename configure_invokeai.py to invokeai_configure.py to be consistent
with installed script name
- Remove warning message about half-precision models not being available
during the model download process.
- adjust estimated file size reported by configure
- guesstimate disk space needed for "all" models
- fix up the "latest" tag to be named 'v2.3-latest'
- To ensure a clean environment, the installer will now detect whether a
previous .venv exists in the install location, and move it to .venv-backup
before creating a fresh .venv.
- Any previous .venv-backup is deleted.
- User is informed of process.
- Rename configure_invokeai.py to invokeai_configure.py to be
consistent with installed script name
- Remove warning message about half-precision models not being
available during the model download process.
- adjust estimated file size reported by configure
- guesstimate disk space needed for "all" models
- fix up the "latest" tag to be named 'v2.3-latest'
`torch` wasn't seeing the environment variable. I suspect this is
because it was imported before the variable was set, so was running with
a different environment.
Many `torch` ops are supported on MPS so this wasn't noticed
immediately, but some samplers like k_dpm_2 still use unsupported
operations and need this fallback.
This PR forces the installer to install the official torch-cu117 wheel
from download.torch.org, rather than relying on PyPi.org to return the
correct version. It ought to correct the problems that some people have
experienced with cuda support not being installed.
1. The convert module was converting ckpt models into
StableDiffusionGeneratorPipeline objects for use in-memory, but then
when saved to disk created files that could not be merged with
StableDiffusionPipeline models. I have added a flag that selects which
pipeline class to return, so that both in-memory and disk conversions
work properly.
2. This PR also fixes an issue with `invoke.sh` not using the correct
path for the textual inversion and merge scripts.
3. Quench nags during the merge process about the safety checker being
turned off.
`torch` wasn't seeing the environment variable. I suspect this is because it was imported before the variable was set, so was running with a different environment.
Many `torch` ops are supported on MPS so this wasn't noticed immediately, but some samplers like k_dpm_2 still use unsupported operations and need this fallback.
* remove non maintained Dockerfile
* adapt Docker related files to latest changes
- also build the frontend when building the image
- skip user response if INVOKE_MODEL_RECONFIGURE is set
- split INVOKE_MODEL_RECONFIGURE to support more than one argument
* rename `docker-build` dir to `docker`
* update build-container.yml
- rename image to invokeai
- add cpu flavor
- add metadata to build summary
- enable caching
- remove build-cloud-img.yml
* fix yarn cache path, link copyjob
Crashes would occur in the invokeai-configure script if no HF token
was found in cache and the user declines to provide one when prompted.
The reason appears to be that on Linux systems getpass_asterisk()
raises an EOFError when no input is provided
On windows10, getpass_asterisk() does not raise the EOFError, but
returns an empty string instead. This patch detects this and raises
the exception so that the control logic is preserved.
if reinstalling over an existing installation where the .venv was
created with symlinks to system python instead of copies of the python
executable, the installer would raise a `SameFileError`, because it
would attempt to copy Python over itself. This fixes the issue.
Copying the executable is still preferred for new environments, because
this guarantees the stable Python version.
- fixes bug in finding the source of the configs dir;
- updates the docs for manual install to clarify the preference to
keeping the `.venv` inside the runtime dir, and the caveat/extra steps
required if done otherwise
if reinstalling over an existing installation where the .venv
was created with symlinks to system python instead of copies
of the python executable, the installer would raise a
SameFileError, because it would attempt to copy Python over
itself. This fixes the issue.
- Added modest adaptive behavior; if the screen is wide enough the three
checklists of models will be arranged in a horizontal row.
- Added color support
## Summary
This PR rewrites the core of the installer in Python for cross-platform
compatibility. Filesystem path manipulation, platform/arch decisions and
various edge cases are handled in a more convenient fashion. The
original `install.bat.in`/`install.sh.in` scripts are kept as
entrypoints for their respective OSs, but only serve as thin wrappers to
the Python module.
In addition, it:
- builds and **packages the .whl with the installer**, so that
downloading a versioned installer will guarantee installation of the
same version of the application.
- updates shell entrypoints:
- new commands are `invokeai`, `invokeai-configure`, `invokeai-ti`,
`invokeai-merge`.
- these commands will be available in the activated `.venv` or via the
launch scripts
- `invoke.py` and `configure_invokeai.py` scripts are deprecated but
kept around for backwards compatibility and keeping users' surprise to a
minimum.
- introduces a new `ldm/invoke/config` package and moves the
`configure_invokeai` script into it. Similarly, movers Textual Inversion
script and TUI to `ldm/invoke/training`.
- moves the `configs` directory into the `ldm/invoke/config` package for
easy distribution.
- updates documentation to reflect all of the above changes
- fixes a failing test
- reduces wheel size to 3MB (from 27MB) by excluding unnecessary image
files under `assets`
⚠️ self-updating functionality and ability to install arbitrary
versions are still WIP. For now we can recommend downloading and running
the installer for a specific version as desired.
## Testing the source install
From the cloned source, check out this branch, and:
`$ python3 installer/main.py --root <path_to_destination>`
Also try:
`$ python3 installer/main.py ` - will prompt for paths
`$ python3 installer/main.py --yes` - will not prompt for any input
- try to combine the `--yes` and `--root` options
- try to install in destinations with "quirky" paths, such as paths
containing spaces in the directory name, etc.
## Testing the packaged install ("Automated Installer"):
Download the
[InvokeAI-installer-v2.3.0+a0.zip](https://github.com/invoke-ai/InvokeAI/files/10533913/InvokeAI-installer-v2.3.0%2Ba0.zip)
file, unzip it, and run the install script for your platform (preferably
in a terminal window)
OR make your own: from the cloned source, check out this branch, and:
```
cd installer
./create_installer.sh
# (do NOT tag/push when prompted! just say "no")
```
This will create the installation media:
`InvokeAI-installer-v2.3.0+a0.zip`. The installer is now
*platform-agnostic* - meaning, both Windows and *nix install resources
are packaged together.
Copy it somewhere as if it had been downloaded from the internet. Unzip
the file, enter the created `InvokeAI-Installer` directory, and run
`install.sh` or `install.bat` as applicable your platform.
⚠️ NOTE!!! `install.sh` accepts the same arguments as are
applicable to the Python script, i.e. you can `install.sh --yes --root
....`. This is NOT yet supported by the Windows `.bat` script. Only
interactive installation is supported on Windows. (this is still a
TODO).
* refactor ckpt_to_diffuser to allow converted pipeline to remain in memory
- This idea was introduced by Damian
- Note that although I attempted to use the updated HuggingFace module
pipelines/stable_diffusion/convert_from_ckpt.py, it was unable to
convert safetensors files for reasons I didn't dig into.
- Default is to extract EMA weights.
* add --ckpt_convert option to load legacy ckpt files as diffusers models
- not quite working - I'm getting artifacts and glitches in the
converted diffuser models
- leave as draft for time being
* do not include safety checker in converted files
* add ability to control which vae is used
API now allows the caller to pass an external VAE model to the
checkpoint conversion process. In this way, if an external VAE is
specified in the checkpoint's config stanza, this VAE will be used
when constructing the diffusers model.
Tested with both regular and inpainting 1.X models.
Not tested with SD 2.X models!
---------
Co-authored-by: Jonathan <34005131+JPPhoto@users.noreply.github.com>
Co-authored-by: Damian Stewart <null@damianstewart.com>
This PR changes the codeowner for the installer directory from
@tildebyte to @ebr due to the former's time commitments.
Further reorganization of the codeowners is pending.
1. only load triton on linux machines
2. require pip >= 23.0 so that editable installs can run without setup.py
3. model files default to SD-1.5, not 2.1
4. use diffusers model of inpainting rather than ckpt
5. selected a new set of initial models based on # of likes at huggingface
- launcher scripts are installed *before* the configure script runs,
so that if something goes wrong in the configure script, the user
can run invoke.{sh,bat} and get the option to re-run configure
- fixed typo in invoke.sh which misspelled name of invokeai-configure
Draft PRs are triggering actions on every commit (except
`test-invoke-pip.yml`).
I've added a conditional to each job to only run when the PR is not a
draft.
(maybe there is a reason we are running all applicable workflows on
draft PRs?)
- also remove conda related things
- rename `invoke` to `invokeai`
- rename `configure_invokeai` to `invokeai-configure`
- rename venv back to common `.venv` but add `--prompt InvokeAI`
- remove outdated information
A new infill method, **solid:** solid color. currently using middle
gray.
Fixes#2417
It seems like the runwayml inpainting model specifically expects those
masked areas to be blanked out like this.
I haven't tried the SD 2.0 inpainting model with it yet.
Otherwise the model seems too reluctant to change these areas, even
though the mask channel should allow it to.
This makes the solid infill method proposed by #2441 less necessary,
though I think there's still a place for an infill method that is faster
than patchmatch and more predictable than tiles.
Even with #2441, this PR is still useful because it influences all areas
to be painted, not just the infill area.
Fixes#2417
- implement the following pattern for finding data files under both
regular and editable install conditions:
import invokeai.foo.bar as bar
path = bar.__path__[0]
- this *seems* to work reliably with Python 3.9. Testing on 3.10 needs
to be performed.
- fixes a spurious "unknown model name" error when trying to edit the
short name of an existing model.
- relaxes naming requirements to include the ':' and '/' characters
in model names
1) Downgrade numpy to avoid dependency conflict with numba
2) Move all non ldm/invoke files into `invokeai`. This includes assets, backend, frontend, and configs.
3) Fix up way that the backend finds the frontend and the generator finds the NSFW caution.png icon.
if running `python3 installer/main.py` from the source distribution,
it would fail because it expected to find a wheel.
this PR tries to perform a source install by going one level up the directory
tree and checking for `pyproject.toml` and `ldm` directory entries to
confirm (to a degree) that this is an InvokeAI distribution
* Update --hires_fix
Change `--hires_fix` to calculate initial width and height based on the model's resolution (if available) and with a minimum size.
- install.sh is now a thin wrapper around the pythonized install script
- install.bat not done yet - to follow
- user messaging is tailored to the current platform (paste shortcuts, file paths, etc)
- emit invoke.sh/invoke.bat scripts to the runtime dir
- improve launch scripts (add help option, etc)
- only emit the platform-specific scripts
if the config directory is missing, initialize it using the standard
process of copying it over, instead of failing to create the config file
this can happen if the user is re-running the config script in a directory which
already has the init file, but no configs dir
the 'setup.py install' method is deprecated in favour of a
build-system independent format: https://peps.python.org/pep-0517/
this is needed to install dependencies that don't have a pyproject.toml
file (only setup.py) in a forward-compatible way
This allows reliable distribution of the initial 'configs' directory
with the Python package, and enables the configuration script to be running
from anywhere, as long as the virtual environment is available on the sys.path
There is a race condition affecting the 'tempfile' module on Windows.
A PermissionsError is raised when cleaning up the temp dir
Python3.10 introduced a flag to suppress this error.
Windows + Python3.9 users will receive an unpleasant stack trace for now
The original textual inversion script in scripts is now superseded. The
replacement can be found in ldm/invoke/textual_inversion.py and is a
merging of the command line and front end scripts. After running `pip
install -e .` there will be a `textual_inversion` command on your path.
You can activate the front end this way:
`textual_inversion -gui`
Adds double-click to reset canvas view to 100%.
- Adds hook to manage single and double clicks
- Single Click `Reset Canvas View` --> scale to fit, no change to
current behaviour
- Double Click `Reset Canvas View` --> set scale to 1
Testing suggests that the diffusers versions of Waifu-1.4 anything-v4.0
require the `sd-vae-ft-mse` to generate decent images, so the
appropriate arguments have been added to the initial model file.
- Model merging and textual inversion scripts have been moved into
`ldm/invoke`, which allows them to be installed properly by
pyproject.toml.
- As part of the pyproject install, the .py suffix is removed from the
command. I.e. use `invoke`, `configure_invokeai`, `merge_models` and
`textual_inversion`.
- GUI versions are activated by adding `--gui` to the command. Without
this, you get a classical argv-based command. Example: `merge_models
--gui`
- Fixed up the launcher scripts to accommodate new naming scheme.
- Keyboard behavior of the GUI front ends has been improved. You can now
use up and down arrow to move from field to field, in addition to <tab>
and ctrl-N/ctrl-P
So far the slider component was unable to take typed input due to a
bunch of issues that were a pain to solve. This PR fixes it.
Things to test:
- Moving the slider also updates the value in the input text box.
- Input text box next to slider can be changed in two ways: If you type
a manual value, the slider will be updated when you lose focus from the
input box. If you use the stepper icons to update the values, the slider
should update immediately.
- Make sure the reset buttons next to the slider are updating correctly
and make sure this updates both the slider and the input box values.
- Brush Size slider -> make sure the hotkeys are updating the input box
too.
- This replaces the original clipseg library with the transformers
version from HuggingFace.
- This should make it possible to register InvokeAI at PyPi and do a
fully automated pip-based install.
- Minor regression: it is no longer possible to specify which device the
clipseg model will be loaded into, and it will reside in CPU. However,
performance is more than acceptable.
- This replaces the original clipseg library with the transformers
version from HuggingFace.
- This should make it possible to register InvokeAI at PyPi and do
a fully automated pip-based install.
- Minor regression: it is no longer possible to specify which device
the clipseg model will be loaded into, and it will reside in CPU.
However, performance is more than acceptable.
Fix two deficiencies in the CLI's support for model management:
1. `!import_model` did not allow user to specify VAE file. This is now
fixed.
2. `!del_model` did not offer the user the opportunity to delete the
underlying
weights file or diffusers directory. This is now fixed.
This PR improves the console reporting of the process of recognizing
trigger tokens and loading their embeds.
1. Do not report "concept is not known to HuggingFace" if the trigger
term is in fact a local embedding trigger.
2. When a trigger term is first recognized during a session, report the
fact.
This should help debug embedding issues in the future.
Note that the local embeddings produced by the new InvokeAI TI training
script default to the format <trigger> with literal angle brackets. This
sets them off from the rest of the text well and will enable
autocomplete at some point in the future. However, this means that they
supersede like-named HuggingFace concepts, and may cause problems for
people uploading them to the HuggingFace repository (although that
problem already exists).
This PR attempts to fix `--free_gpu_mem` option that was not working in
CKPT-based diffuser model after #1583.
I noticed that the memory usage after #1583 did not decrease after
generating an image when `--free_gpu_mem` option was enabled.
It turns out that the option was not propagated into `Generator`
instance, hence the generation will always run without the memory saving
procedure.
This PR also related to #2326. Initially, I was trying to make
`--free_gpu_mem` works on 🤗 diffuser model as well.
In the process, I noticed that InvokeAI will raise an exception when
`--free_gpu_mem` is enabled.
I tried to quickly fix it by simply ignoring the exception and produce a
warning message to user's console.
This PR adds `scripts/merge_fe.py`, which will merge any 2-3 diffusers
models registered in InvokeAI's `models.yaml`, producing a new merged
model that will be registered as well.
Currently this script will only work if all models to be merged are
known by their repo_ids. Local models, including those converted from
ckpt files, will cause a crash due to a bug in the diffusers
`checkpoint_merger.py` code. I have made a PR against
huggingface/diffusers which fixes this:
https://github.com/huggingface/diffusers/pull/2060
I've written up the install procedure for xFormers on Linux systems.
I need help with the Windows install; I don't know what the build
dependencies (compiler, etc) are. This section of the docs is currently
empty.
Please see `docs/installation/070_INSTALL_XFORMERS.md`
other changes which where required:
- move configure_invokeai.py into ldm.invoke
- update files which imported configure_invokeai to use new location:
- ldm/invoke/CLI.py
- scripts/load_models.py
- scripts/preload_models.py
- update test-invoke-pip.yml:
- remove pr type "converted_to_draft"
- remove reference to dev/diffusers
- remove no more needed requirements from matrix
- add pytorch to matrix
- install via `pip3 install --use-pep517 .`
- use the created executables
- this should also fix configure_invoke not executed in windows
To install use `pip install --use-pep517 -e .` where `-e` is optional
- Added new documentation for textual inversion training process
- Move `main.py` into the deprecated scripts folder
- Fix bug in `textual_inversion.py` which was causing it to not load
the globals module correctly.
- Sort models alphabetically in console front end
- Only show diffusers models in console front end
Starting `invoke.py` with --no-xformers will disable
memory-efficient-attention support if xformers is installed.
For symmetry, `--xformers` will enable support, but this is already the
default if xformers is available.
This commit suppresses a few irrelevant warning messages that the
diffusers module produces:
1. The warning that turning off the NSFW detector makes you an
irresponsible person.
2. Warnings about running fp16 models stored in CPU (we are not running
them in CPU, just caching them in CPU RAM)
This commit suppresses a few irrelevant warning messages that the
diffusers module produces:
1. The warning that turning off the NSFW detector makes you an
irresponsible person.
2. Warnings about running fp16 models stored in CPU (we are not running
them in CPU, just caching them in CPU RAM)
Starting `invoke.py` with --no-xformers will disable
memory-efficient-attention support if xformers is installed.
--xformers will enable support, but this is already the
default.
- During trigger token processing, emit better status messages indicating
which triggers were found.
- Suppress message "<token> is not known to HuggingFace library, when
token is in fact a local embed.
- When a ckpt or safetensors file uses an external autoencoder and we
don't know which diffusers model corresponds to this (if any!), then
we fallback to using stabilityai/sd-vae-ft-mse
- This commit improves error reporting so that user knows what is happening.
- After successfully converting a ckt file to diffusers, model_manager
will attempt to create an equivalent 'vae' entry to the resulting
diffusers stanza.
- This is a bit of a hack, as it relies on a hard-coded dictionary
to map ckpt VAEs to diffusers VAEs. The correct way to do this
would be to convert the VAE to a diffusers model and then point
to that. But since (almost) all models are using vae-ft-mse-840000-ema-pruned,
I did it the easy way first and will work on the better solution later.
1. !import_model did not allow user to specify VAE file. This is now fixed.
2. !del_model did not offer the user the opportunity to delete the underlying
weights file or diffusers directory. This is now fixed.
This commit allows InvokeAI to store & load 🤗 models at a location set
by `XDG_CACHE_HOME` environment variable if `HF_HOME` is not set.
By integrating this commit, a user who either use `HF_HOME` or
`XDG_CACHE_HOME` environment variables in their environment can let
InvokeAI to reuse the existing cache directory used by 🤗 library by
default. I happened to benefit from this commit because I have a Jupyter
Notebook that uses 🤗 diffusers model stored at `XDG_CACHE_HOME`
directory.
Reference:
https://huggingface.co/docs/huggingface_hub/main/en/package_reference/environment_variables#xdgcachehome
Updated the link for the MS Visual C libraries - I'm not sure if MS
changed the location of the files but this new one leads right to the
file downloads.
- Migration process will not crash if duplicate model files are found,
one in legacy location and the other in new location. The model in the
legacy location will be deleted in this case.
- Added a hint to stable-diffusion-2.1 telling people it will work best
with 768 pixel images.
- Added the anything-4.0 model.
Added a --default_only argument that limits model downloads to the
single default model, for use in continuous integration.
New behavior
- switch -
--yes --default_only Behavior
----- -------------- --------
<not set> <not set> interactive download
--yes <not set> non-interactively download all
recommended models
--yes --default_only non-interactively download the
default model
Added a --default_only argument that limits model downloads to the single
default model, for use in continuous integration.
New behavior
- switch -
--yes --default_only Behavior
----- -------------- --------
<not set> <not set> interactive download
--yes <not set> non-interactively download all
recommended models
--yes --default_only non-interactively download the
default model
- All tensors in diffusers code path are now set explicitly to
float32 or float16, depending on the --precision flag.
- autocast is still used in the ckpt path, since it is being
deprecated.
- Work around problem with OmegaConf.update() that prevented model names
from containing periods.
- Fix logic bug in !delete_model that didn't check for existence of model
in config file.
* docs: Fix links to pip and Conda installation methods
* docs: Improve installation script readability
This commit adds a space between `-m` option and the module name.
* docs: Fix alignments of step 4 & 9 in `pip` installation method
* docs: Rewrite step 10 of the ` pip` installation method
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
- Migration process will not crash if duplicate model files are found,
one in legacy location and the other in new location.
The model in the legacy location will be deleted in this case.
- Added a hint to stable-diffusion-2.1 telling people it will work best
with 768 pixel images.
- Added the anything-4.0 model.
* initial commit of DiffusionPipeline class
* spike: proof of concept using diffusers for txt2img
* doc: type hints for Generator
* refactor(model_cache): factor out load_ckpt
* model_cache: add ability to load a diffusers model pipeline
and update associated things in Generate & Generator to not instantly fail when that happens
* model_cache: fix model default image dimensions
* txt2img: support switching diffusers schedulers
* diffusers: let the scheduler do its scaling of the initial latents
Remove IPNDM scheduler; it is not behaving.
* web server: update image_progress callback for diffusers data
* diffusers: restore prompt weighting feature
* diffusers: fix set-sampler error following model switch
* diffusers: use InvokeAIDiffuserComponent for conditioning
* cross_attention_control: stub (no-op) implementations for diffusers
* model_cache: let offload_model work with DiffusionPipeline, sorta.
* models.yaml.example: add diffusers-format model, set as default
* test-invoke-conda: use diffusers-format model
test-invoke-conda: put huggingface-token where the library can use it
* environment-mac: upgrade to diffusers 0.7 (from 0.6)
this was already done for linux; mac must have been lost in the merge.
* preload_models: explicitly load diffusers models
In non-interactive mode too, as long as you're logged in.
* fix(model_cache): don't check `model.config` in diffusers format
clean-up from recent merge.
* diffusers integration: support img2img
* dev: upgrade to diffusers 0.8 (from 0.7.1)
We get to remove some code by using methods that were factored out in the base class.
* refactor: remove backported img2img.get_timesteps
now that we can use it directly from diffusers 0.8.1
* ci: use diffusers model
* dev: upgrade to diffusers 0.9 (from 0.8.1)
* lint: correct annotations for Python 3.9.
* lint: correct AttributeError.name reference for Python 3.9.
* CI: prefer diffusers-1.4 because it no longer requires a token
The RunwayML models still do.
* build: there's yet another place to update requirements?
* configure: try to download models even without token
Models in the CompVis and stabilityai repos no longer require them. (But runwayml still does.)
* configure: add troubleshooting info for config-not-found
* fix(configure): prepend root to config path
* fix(configure): remove second `default: true` from models example
* CI: simplify test-on-push logic now that we don't need secrets
The "test on push but only in forks" logic was only necessary when tests didn't work for PRs-from-forks.
* create an embedding_manager for diffusers
* internal: avoid importing diffusers DummyObject
see https://github.com/huggingface/diffusers/issues/1479
* fix "config attributes…not expected" diffusers warnings.
* fix deprecated scheduler construction
* work around an apparent MPS torch bug that causes conditioning to have no effect
* 🚧 post-rebase repair
* preliminary support for outpainting (no masking yet)
* monkey-patch diffusers.attention and use Invoke lowvram code
* add always_use_cpu arg to bypass MPS
* add cross-attention control support to diffusers (fails on MPS)
For unknown reasons MPS produces garbage output with .swap(). Use
--always_use_cpu arg to invoke.py for now to test this code on MPS.
* diffusers support for the inpainting model
* fix debug_image to not crash with non-RGB images.
* inpainting for the normal model [WIP]
This seems to be performing well until the LAST STEP, at which point it dissolves to confetti.
* fix off-by-one bug in cross-attention-control (#1774)
prompt token sequences begin with a "beginning-of-sequence" marker <bos> and end with a repeated "end-of-sequence" marker <eos> - to make a default prompt length of <bos> + 75 prompt tokens + <eos>. the .swap() code was failing to take the column for <bos> at index 0 into account. the changes here do that, and also add extra handling for a single <eos> (which may be redundant but which is included for completeness).
based on my understanding and some assumptions about how this all works, the reason .swap() nevertheless seemed to do the right thing, to some extent, is because over multiple steps the conditioning process in Stable Diffusion operates as a feedback loop. a change to token n-1 has flow-on effects to how the [1x4x64x64] latent tensor is modified by all the tokens after it, - and as the next step is processed, all the tokens before it as well. intuitively, a token's conditioning effects "echo" throughout the whole length of the prompt. so even though the token at n-1 was being edited when what the user actually wanted was to edit the token at n, it nevertheless still had some non-negligible effect, in roughly the right direction, often enough that it seemed like it was working properly.
* refactor common CrossAttention stuff into a mixin so that the old ldm code can still work if necessary
* inpainting for the normal model. I think it works this time.
* diffusers: reset num_vectors_per_token
sync with 44a0055571
* diffusers: txt2img2img (hires_fix)
with so much slicing and dicing of pipeline methods to stitch them together
* refactor(diffusers): reduce some code duplication amongst the different tasks
* fixup! refactor(diffusers): reduce some code duplication amongst the different tasks
* diffusers: enable DPMSolver++ scheduler
* diffusers: upgrade to diffusers 0.10, add Heun scheduler
* diffusers(ModelCache): stopgap to make from_cpu compatible with diffusers
* CI: default to diffusers-1.5 now that runwayml token requirement is gone
* diffusers: update to 0.10 (and transformers to 4.25)
* diffusers: use xformers when available
diffusers no longer auto-enables this as of 0.10.2.
* diffusers: make masked img2img behave better with multi-step schedulers
re-randomizing the noise each step was confusing them.
* diffusers: work more better with more models.
fixed relative path problem with local models.
fixed models on hub not always having a `fp16` branch.
* diffusers: stopgap fix for attention_maps_callback crash after recent merge
* fixup import merge conflicts
correction for 061c5369a2
* test: add tests/inpainting inputs for masked img2img
* diffusers(AddsMaskedGuidance): partial fix for k-schedulers
Prevents them from crashing, but results are still hot garbage.
* fix --safety_checker arg parsing
and add note to diffusers loader about where safety checker gets called
* generate: fix import error
* CI: don't try to read the old init location
* diffusers: support loading an alternate VAE
* CI: remove sh-syntax if-statement so it doesn't crash powershell
* CI: fold strings in yaml because backslash is not line-continuation in powershell
* attention maps callback stuff for diffusers
* build: fix syntax error in environment-mac
* diffusers: add INITIAL_MODELS with diffusers-compatible repos
* re-enable the embedding manager; closes#1778
* Squashed commit of the following:
commit e4a956abc37fcb5cf188388b76b617bc5c8fda7d
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 15:43:07 2022 +0100
import new load handling from EmbeddingManager and cleanup
commit c4abe91a5ba0d415b45bf734068385668b7a66e6
Merge: 032e856e 1efc6397
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 15:09:53 2022 +0100
Merge branch 'feature_textual_inversion_mgr' into dev/diffusers_with_textual_inversion_manager
commit 032e856eefb3bbc39534f5daafd25764bcfcef8b
Merge: 8b4f0fe9 bc515e24
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 15:08:01 2022 +0100
Merge remote-tracking branch 'upstream/dev/diffusers' into dev/diffusers_with_textual_inversion_manager
commit 1efc6397fc6e61c1aff4b0258b93089d61de5955
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 15:04:28 2022 +0100
cleanup and add performance notes
commit e400f804ac471a0ca2ba432fd658778b20c7bdab
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 14:45:07 2022 +0100
fix bug and update unit tests
commit deb9ae0ae1016750e93ce8275734061f7285a231
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 14:28:29 2022 +0100
textual inversion manager seems to work
commit 162e02505dec777e91a983c4d0fb52e950d25ff0
Merge: cbad4583 12769b3d
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 11:58:03 2022 +0100
Merge branch 'main' into feature_textual_inversion_mgr
commit cbad45836c6aace6871a90f2621a953f49433131
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 11:54:10 2022 +0100
use position embeddings
commit 070344c69b0e0db340a183857d0a787b348681d3
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 11:53:47 2022 +0100
Don't crash CLI on exceptions
commit b035ac8c6772dfd9ba41b8eeb9103181cda028f8
Author: Damian Stewart <d@damianstewart.com>
Date: Sun Dec 18 11:11:55 2022 +0100
add missing position_embeddings
commit 12769b3d3562ef71e0f54946b532ad077e10043c
Author: Damian Stewart <d@damianstewart.com>
Date: Fri Dec 16 13:33:25 2022 +0100
debugging why it don't work
commit bafb7215eabe1515ca5e8388fd3bb2f3ac5362cf
Author: Damian Stewart <d@damianstewart.com>
Date: Fri Dec 16 13:21:33 2022 +0100
debugging why it don't work
commit 664a6e9e14
Author: Damian Stewart <d@damianstewart.com>
Date: Fri Dec 16 12:48:38 2022 +0100
use TextualInversionManager in place of embeddings (wip, doesn't work)
commit 8b4f0fe9d6e4e2643b36dfa27864294785d7ba4e
Author: Damian Stewart <d@damianstewart.com>
Date: Fri Dec 16 12:48:38 2022 +0100
use TextualInversionManager in place of embeddings (wip, doesn't work)
commit ffbe1ab11163ba712e353d89404e301d0e0c6cdf
Merge: 6e4dad60023df37e
Author: Damian Stewart <d@damianstewart.com>
Date: Fri Dec 16 02:37:31 2022 +0100
Merge branch 'feature_textual_inversion_mgr' into dev/diffusers
commit 023df37eff
Author: Damian Stewart <d@damianstewart.com>
Date: Fri Dec 16 02:36:54 2022 +0100
cleanup
commit 05fac594ea
Author: Damian Stewart <d@damianstewart.com>
Date: Fri Dec 16 02:07:49 2022 +0100
tweak error checking
commit 009f32ed39
Author: damian <null@damianstewart.com>
Date: Thu Dec 15 21:29:47 2022 +0100
unit tests passing for embeddings with vector length >1
commit beb1b08d9a
Author: Damian Stewart <d@damianstewart.com>
Date: Thu Dec 15 13:39:09 2022 +0100
more explicit equality tests when overwriting
commit 44d8a5a7c8
Author: Damian Stewart <d@damianstewart.com>
Date: Thu Dec 15 13:30:13 2022 +0100
wip textual inversion manager (unit tests passing for 1v embedding overwriting)
commit 417c2b57d9
Author: Damian Stewart <d@damianstewart.com>
Date: Thu Dec 15 12:30:55 2022 +0100
wip textual inversion manager (unit tests passing for base stuff + padding)
commit 2e80872e3b
Author: Damian Stewart <d@damianstewart.com>
Date: Thu Dec 15 10:57:57 2022 +0100
wip new TextualInversionManager
* stop using WeightedFrozenCLIPEmbedder
* store diffusion models locally
- configure_invokeai.py reconfigured to store diffusion models rather than
CompVis models
- hugging face caching model is used, but cache is set to ~/invokeai/models/repo_id
- models.yaml does **NOT** use path, just repo_id
- "repo_name" changed to "repo_id" to following hugging face conventions
- Models are loaded with full precision pending further work.
* allow non-local files during development
* path takes priority over repo_id
* MVP for model_cache and configure_invokeai
- Feature complete (almost)
- configure_invokeai.py downloads both .ckpt and diffuser models,
along with their VAEs. Both types of download are controlled by
a unified INITIAL_MODELS.yaml file.
- model_cache can load both type of model and switches back and forth
in CPU. No memory leaks detected
TO DO:
1. I have not yet turned on the LocalOnly flag for diffuser models, so
the code will check the Hugging Face repo for updates before using the
locally cached models. This will break firewalled systems. I am thinking
of putting in a global check for internet connectivity at startup time
and setting the LocalOnly flag based on this. It would be good to check
updates if there is connectivity.
2. I have not gone completely through INITIAL_MODELS.yaml to check which
models are available as diffusers and which are not. So models like
PaperCut and VoxelArt may not load properly. The runway and stability
models are checked, as well as the Trinart models.
3. Add stanzas for SD 2.0 and 2.1 in INITIAL_MODELS.yaml
REMAINING PROBLEMS NOT DIRECTLY RELATED TO MODEL_CACHE:
1. When loading a .ckpt file there are lots of messages like this:
Warning! ldm.modules.attention.CrossAttention is no longer being
maintained. Please use InvokeAICrossAttention instead.
I'm not sure how to address this.
2. The ckpt models ***don't actually run*** due to the lack of special-case
support for them in the generator objects. For example, here's the hard
crash you get when you run txt2img against the legacy waifu-diffusion-1.3
model:
```
>> An error occurred:
Traceback (most recent call last):
File "/data/lstein/InvokeAI/ldm/invoke/CLI.py", line 140, in main
main_loop(gen, opt)
File "/data/lstein/InvokeAI/ldm/invoke/CLI.py", line 371, in main_loop
gen.prompt2image(
File "/data/lstein/InvokeAI/ldm/generate.py", line 496, in prompt2image
results = generator.generate(
File "/data/lstein/InvokeAI/ldm/invoke/generator/base.py", line 108, in generate
image = make_image(x_T)
File "/data/lstein/InvokeAI/ldm/invoke/generator/txt2img.py", line 33, in make_image
pipeline_output = pipeline.image_from_embeddings(
File "/home/lstein/invokeai/.venv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1265, in __getattr__
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'LatentDiffusion' object has no attribute 'image_from_embeddings'
```
3. The inpainting diffusion model isn't working. Here's the output of "banana
sushi" when inpainting-1.5 is loaded:
```
Traceback (most recent call last):
File "/data/lstein/InvokeAI/ldm/generate.py", line 496, in prompt2image
results = generator.generate(
File "/data/lstein/InvokeAI/ldm/invoke/generator/base.py", line 108, in generate
image = make_image(x_T)
File "/data/lstein/InvokeAI/ldm/invoke/generator/txt2img.py", line 33, in make_image
pipeline_output = pipeline.image_from_embeddings(
File "/data/lstein/InvokeAI/ldm/invoke/generator/diffusers_pipeline.py", line 301, in image_from_embeddings
result_latents, result_attention_map_saver = self.latents_from_embeddings(
File "/data/lstein/InvokeAI/ldm/invoke/generator/diffusers_pipeline.py", line 330, in latents_from_embeddings
result: PipelineIntermediateState = infer_latents_from_embeddings(
File "/data/lstein/InvokeAI/ldm/invoke/generator/diffusers_pipeline.py", line 185, in __call__
for result in self.generator_method(*args, **kwargs):
File "/data/lstein/InvokeAI/ldm/invoke/generator/diffusers_pipeline.py", line 367, in generate_latents_from_embeddings
step_output = self.step(batched_t, latents, guidance_scale,
File "/home/lstein/invokeai/.venv/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/data/lstein/InvokeAI/ldm/invoke/generator/diffusers_pipeline.py", line 409, in step
step_output = self.scheduler.step(noise_pred, timestep, latents, **extra_step_kwargs)
File "/home/lstein/invokeai/.venv/lib/python3.9/site-packages/diffusers/schedulers/scheduling_lms_discrete.py", line 223, in step
pred_original_sample = sample - sigma * model_output
RuntimeError: The size of tensor a (9) must match the size of tensor b (4) at non-singleton dimension 1
```
* proper support for float32/float16
- configure script now correctly detects user's preference for
fp16/32 and downloads the correct diffuser version. If fp16
version not available, falls back to fp32 version.
- misc code cleanup and simplification in model_cache
* add on-the-fly conversion of .ckpt to diffusers models
1. On-the-fly conversion code can be found in the file ldm/invoke/ckpt_to_diffusers.py.
2. A new !optimize command has been added to the CLI. Should be ported to Web GUI.
User experience on the CLI is this:
```
invoke> !optimize /home/lstein/invokeai/models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
INFO: Converting legacy weights file /home/lstein/invokeai/models/ldm/stable-diffusion-v1/sd-v1-4.ckpt to optimized diffuser model.
This operation will take 30-60s to complete.
Success. Optimized model is now located at /home/lstein/tmp/invokeai/models/optimized-ckpts/sd-v1-4
Writing new config file entry for sd-v1-4...
>> New configuration:
sd-v1-4:
description: Optimized version of sd-v1-4
format: diffusers
path: /home/lstein/tmp/invokeai/models/optimized-ckpts/sd-v1-4
OK to import [n]? y
>> Verifying that new model loads...
>> Current VRAM usage: 2.60G
>> Offloading stable-diffusion-2.1 to CPU
>> Loading diffusers model from /home/lstein/tmp/invokeai/models/optimized-ckpts/sd-v1-4
| Using faster float16 precision
You have disabled the safety checker for <class 'ldm.invoke.generator.diffusers_pipeline.StableDiffusionGeneratorPipeline'> by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion \
license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances,\
disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .
| training width x height = (512 x 512)
>> Model loaded in 3.48s
>> Max VRAM used to load the model: 2.17G
>> Current VRAM usage:2.17G
>> Textual inversions available:
>> Setting Sampler to k_lms (LMSDiscreteScheduler)
Keep model loaded? [y]
```
* add parallel set of generator files for ckpt legacy generation
* generation using legacy ckpt models now working
* diffusers: fix missing attention_maps_callback
fix for 23eb80b404
* associate legacy CrossAttention with .ckpt models
* enable autoconvert
New --autoconvert CLI option will scan a designated directory for
new .ckpt files, convert them into diffuser models, and import
them into models.yaml.
Works like this:
invoke.py --autoconvert /path/to/weights/directory
In ModelCache added two new methods:
autoconvert_weights(config_path, weights_directory_path, models_directory_path)
convert_and_import(ckpt_path, diffuser_path)
* diffusers: update to diffusers 0.11 (from 0.10.2)
* fix vae loading & width/height calculation
* refactor: encapsulate these conditioning data into one container
* diffusers: fix some noise-scaling issues by pushing the noise-mixing down to the common function
* add support for safetensors and accelerate
* set local_files_only when internet unreachable
* diffusers: fix error-handling path when model repo has no fp16 branch
* fix generatorinpaint error
Fixes :
"ModuleNotFoundError: No module named 'ldm.invoke.generatorinpaint'
https://github.com/invoke-ai/InvokeAI/pull/1583#issuecomment-1363634318
* quench diffuser safety-checker warning
* diffusers: support stochastic DDIM eta parameter
* fix conda env creation on macos
* fix cross-attention with diffusers 0.11
* diffusers: the VAE needs to be tiling as well as the U-Net
* diffusers: comment on subfolders
* diffusers: embiggen!
* diffusers: make model_cache.list_models serializable
* diffusers(inpaint): restore scaling functionality
* fix requirements clash between numba and numpy 1.24
* diffusers: allow inpainting model to do non-inpainting tasks
* start expanding model_cache functionality
* add import_ckpt_model() and import_diffuser_model() methods to model_manager
- in addition, model_cache.py is now renamed to model_manager.py
* allow "recommended" flag to be optional in INITIAL_MODELS.yaml
* configure_invokeai now downloads VAE diffusers in advance
* rename ModelCache to ModelManager
* remove support for `repo_name` in models.yaml
* check for and refuse to load embeddings trained on incompatible models
* models.yaml.example: s/repo_name/repo_id
and remove extra INITIAL_MODELS now that the main one has diffusers models in it.
* add MVP textual inversion script
* refactor(InvokeAIDiffuserComponent): factor out _combine()
* InvokeAIDiffuserComponent: implement threshold
* InvokeAIDiffuserComponent: diagnostic logs for threshold
...this does not look right
* add a curses-based frontend to textual inversion
- not quite working yet
- requires npyscreen installed
- on windows will also have the windows-curses requirement, but not added
to requirements yet
* add curses-based interface for textual inversion
* fix crash in convert_and_import()
- This corrects a "local variable referenced before assignment" error
in model_manager.convert_and_import()
* potential workaround for no 'state_dict' key error
- As reported in https://github.com/huggingface/diffusers/issues/1876
* create TI output dir if needed
* Update environment-lin-cuda.yml (#2159)
Fixing line 42 to be the proper order to define the transformers requirement: ~= instead of =~
* diffusers: update sampler-to-scheduler mapping
based on https://github.com/huggingface/diffusers/issues/277#issuecomment-1371428672
* improve user exp for ckt to diffusers conversion
- !optimize_models command now operates on an existing ckpt file entry in models.yaml
- replaces existing entry, rather than adding a new one
- offers to delete the ckpt file after conversion
* web: adapt progress callback to deal with old generator or new diffusers pipeline
* clean-up model_manager code
- add_model() verified to work for .ckpt local paths,
.ckpt remote URLs, diffusers local paths, and
diffusers repo_ids
- convert_and_import() verified to work for local and
remove .ckpt files
* handle edge cases for import_model() and convert_model()
* add support for safetensor .ckpt files
* fix name error
* code cleanup with pyflake
* improve model setting behavior
- If the user enters an invalid model name at startup time, will not
try to load it, warn, and use default model
- CLI UI enhancement: include currently active model in the command
line prompt.
* update test-invoke-pip.yml
- fix model cache path to point to runwayml/stable-diffusion-v1-5
- remove `skip-sd-weights` from configure_invokeai.py args
* exclude dev/diffusers from "fail for draft PRs"
* disable "fail on PR jobs"
* re-add `--skip-sd-weights` since no space
* update workflow environments
- include `INVOKE_MODEL_RECONFIGURE: '--yes'`
* clean up model load failure handling
- Allow CLI to run even when no model is defined or loadable.
- Inhibit stack trace when model load fails - only show last error
- Give user *option* to run configure_invokeai.py when no models
successfully load.
- Restart invokeai after reconfiguration.
* further edge-case handling
1) only one model in models.yaml file, and that model is broken
2) no models in models.yaml
3) models.yaml doesn't exist at all
* fix incorrect model status listing
- "cached" was not being returned from list_models()
- normalize handling of exceptions during model loading:
- Passing an invalid model name to generate.set_model() will return
a KeyError
- All other exceptions are returned as the appropriate Exception
* CI: do download weights (if not already cached)
* diffusers: fix scheduler loading in offline mode
* CI: fix model name (no longer has `diffusers-` prefix)
* Update txt2img2img.py (#2256)
* fixes to share models with HuggingFace cache system
- If HF_HOME environment variable is defined, then all huggingface models
are stored in that directory following the standard conventions.
- For seamless interoperability, set HF_HOME to ~/.cache/huggingface
- If HF_HOME not defined, then models are stored in ~/invokeai/models.
This is equivalent to setting HF_HOME to ~/invokeai/models
A future commit will add a migration mechanism so that this change doesn't
break previous installs.
* feat - make model storage compatible with hugging face caching system
This commit alters the InvokeAI model directory to be compatible with
hugging face, making it easier to share diffusers (and other models)
across different programs.
- If the HF_HOME environment variable is not set, then models are
cached in ~/invokeai/models in a format that is identical to the
HuggingFace cache.
- If HF_HOME is set, then models are cached wherever HF_HOME points.
- To enable sharing with other HuggingFace library clients, set
HF_HOME to ~/.cache/huggingface to set the default cache location
or to ~/invokeai/models to have huggingface cache inside InvokeAI.
* fixes to share models with HuggingFace cache system
- If HF_HOME environment variable is defined, then all huggingface models
are stored in that directory following the standard conventions.
- For seamless interoperability, set HF_HOME to ~/.cache/huggingface
- If HF_HOME not defined, then models are stored in ~/invokeai/models.
This is equivalent to setting HF_HOME to ~/invokeai/models
A future commit will add a migration mechanism so that this change doesn't
break previous installs.
* fix error "no attribute CkptInpaint"
* model_manager.list_models() returns entire model config stanza+status
* Initial Draft - Model Manager Diffusers
* added hash function to diffusers
* implement sha256 hashes on diffusers models
* Add Model Manager Support for Diffusers
* fix various problems with model manager
- in cli import functions, fix not enough values to unpack from
_get_name_and_desc()
- fix crash when using old-style vae: value with new-style diffuser
* rebuild frontend
* fix dictconfig-not-serializable issue
* fix NoneType' object is not subscriptable crash in model_manager
* fix "str has no attribute get" error in model_manager list_models()
* Add path and repo_id support for Diffusers Model Manager
Also fixes bugs
* Fix tooltip IT localization not working
* Add Version Number To WebUI
* Optimize Model Search
* Fix incorrect font on the Model Manager UI
* Fix image degradation on merge fixes - [Experimental]
This change should effectively fix a couple of things.
- Fix image degradation on subsequent merges of the canvas layers.
- Fix the slight transparent border that is left behind when filling the bounding box with a color.
- Fix the left over line of color when filling a bounding box with color.
So far there are no side effects for this. If any, please report.
* Add local model filtering for Diffusers / Checkpoints
* Go to home on modal close for the Add Modal UI
* Styling Fixes
* Model Manager Diffusers Localization Update
* Add Safe Tensor scanning to Model Manager
* Fix model edit form dispatching string values instead of numbers.
* Resolve VAE handling / edge cases for supplied repos
* defer injecting tokens for textual inversions until they're used for the first time
* squash a console warning
* implement model migration check
* add_model() overwrites previous config rather than merges
* fix model config file attribute merging
* fix precision handling in textual inversion script
* allow ckpt conversion script to work with safetensors .ckpts
Applied patch here:
beb932c5d1
* fix name "args" is not defined crash in textual_inversion_training
* fix a second NameError: name 'args' is not defined crash
* fix loading of the safety checker from the global cache dir
* add installation step to textual inversion frontend
- After a successful training run, the script will copy learned_embeds.bin
to a subfolder of the embeddings directory.
- User given the option to delete the logs and intermediate checkpoints
(which together use 7-8G of space)
- If textual inversion training fails, reports the error gracefully.
* don't crash out on incompatible embeddings
- put try: blocks around places where the system tries to load an embedding
which is incompatible with the currently loaded model
* add support for checkpoint resuming
* textual inversion preferences are saved and restored between sessions
- Preferences are stored in a file named text-inversion-training/preferences.conf
- Currently the resume-from-checkpoint option is not working correctly. Possible
bug in textual_inversion_training.py?
* copy learned_embeddings.bin into right location
* add front end for diffusers model merging
- Front end doesn't do anything yet!!!!
- Made change to model name parsing in CLI to support ability to have merged models
with the "+" character in their names.
* improve inpainting experience
- recommend ckpt version of inpainting-1.5 to user
- fix get_noise() bug in ckpt version of omnibus.py
* update environment*yml
* tweak instructions to install HuggingFace token
* bump version number
* enhance update scripts
- update scripts will now fetch new INITIAL_MODELS.yaml so that
configure_invokeai.py will know about the diffusers versions.
* enhance invoke.sh/invoke.bat launchers
- added configure_invokeai.py to menu
- menu defaults to browser-based invoke
* remove conda workflow (#2321)
* fix `token_ids has shape torch.Size([79]) - expected [77]`
* update CHANGELOG.md with 2.3.* info
- Add information on how formats have changed and the upgrade process.
- Add short bug list.
Co-authored-by: Damian Stewart <d@damianstewart.com>
Co-authored-by: Damian Stewart <null@damianstewart.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
Co-authored-by: Wybartel-luxmc <37852506+Wybartel-luxmc@users.noreply.github.com>
Co-authored-by: mauwii <Mauwii@outlook.de>
Co-authored-by: mickr777 <115216705+mickr777@users.noreply.github.com>
Co-authored-by: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Co-authored-by: Eugene Brodsky <ebr@users.noreply.github.com>
Co-authored-by: Matthias Wild <40327258+mauwii@users.noreply.github.com>
* update version number
* print version number at startup
* move version number into ldm/invoke/_version.py
* bump version to 2.2.6+a0
* handle whitespace better
* resolve issues raised by mauwii during PR review
1. create_installers.sh now asks before tagging and committing the
current repo
2. trailing whitespace removed from user-provided location of invokeai
directory in install.bat
Updated the link for the MS Visual C libraries - I'm not sure if MS changed the location of the files but this new one leads right to the file downloads.
- Removed links from the install instructions to the installer zip files.
- Replaced "2.2.4" with "2.X.X" globally, to avoid the docs going out of
date.
* Permit cmd override for CORS modification
* Enable multiple origins for CORS
* Remove CMD_OVERRIDE
* Revert executable bit change
* Defensively convert list into string
* Bad if statement
* Retry rebase
* Retry rebase
Co-authored-by: Chris Dawson <chris@vivoh.com>
- fix problem of facexlib weights being downloaded into the .venv
package directory when codeformer restoration requested.
- now users pre-downloaded weights in ~/invokeai/models/gfpgan/weights
(which is shared with gfpgan)
Co-authored-by: Matthias Wild <40327258+mauwii@users.noreply.github.com>
- Fixed codeformer module so that the facexlib files are downloaded
into their pre-stored location in models/gfpgan/weights (shared
with the GFPGAN module)
* installer tweaks in preparation for v2.2.5
- pin numpy to 1.23.* to avoid requirements conflict with numba
- update.sh and update.bat now accept a tag or branch string, not a URL
- update scripts download latest requirements-base before updating.
* update.bat.in debugged and working
* update pulls from "latest" now
* bump version number
* fix permissions on create_installer.sh
* give Linux user option of installing ROCm or CUDA
* rc2.2.5 (install.sh) relative path fixes (#2155)
* (installer) fix bug in resolution of relative paths in linux install script
point installer at 2.2.5-rc1
selecting ~/Data/myapps/ as location would create a ./~/Data/myapps
instead of expanding the ~/ to the value of ${HOME}
also, squash the trailing slash in path, if it was entered by the user
* (installer) add option to automatically start the app after install
also: when exiting, print the command to get back into the app
* remove extraneous whitespace
* model_cache applies rootdir to config path
* bring installers up to date with 2.2.5-rc2
* bump rc version
* create_installer now adds version number
* rebuild frontend
* bump rc#
* add locales to frontend dist package
- bump to patchlevel 6
* bump patchlevel
* use invoke-ai version of GFPGAN
- This version is very slightly modified to allow weights files
to be pre-downloaded by the configure script.
* fix formatting error during startup
* bump patch level
* workaround #2 for GFPGAN facexlib() weights downloading
* bump patch
* ready for merge and release
* remove extraneous comment
* set PYTORCH_ENABLE_MPS_FALLBACK directly in invoke.py
Co-authored-by: Eugene Brodsky <ebr@users.noreply.github.com>
* Update WEBUIHOTKEYS.md
Fixed display errors so it no longer show extra plus signs on the site
* Update WEBUIHOTKEYS.md
Correction to keycap look to have symbols on special keys like enter, shift, and ctrl.
- A couple of users have reported that switching back and forth
between ckpt models is causing a "GPU out of memory" crash.
Traceback suggests there is actually a CPU RAM issue.
- This speculative test simply performs a round of garbage collection
before the point where the crash occurs.
* Initial Localization Implementation
* Fix Initial Spinner
* Language Picker Dropdown
* RU Localization Update
Co-Authored-By: Artur <83028930+netsvetaev@users.noreply.github.com>
* Fixed localization breaking themes
* useUpdateTranslation Hook
To force trigger translations for data objects
* Localize Tab Data
* Localize Prompt Input & Current Image Buttons
* Localize Gallery & Bug FIxes
Fix a bug where the delete image from the context menu wasn't working. Removed tooltips that were broken as they don't work in context menu.
* Fix localization breaking in production
* Add Toast Localization Support
* Localize Unified Canvas
* Localize WIP Tabs
* Localize Hotkeys
* Localize Settings
* RU Localization Update
Co-Authored-By: Artur <83028930+netsvetaev@users.noreply.github.com>
* Add Support for Italian and Portuguese
* Localize Toasts
* Fix width of language picker items
* Localize Backend Messages
* Disable Debug Messages
* Add Support for French
* Fix missing localization for a string in the SettingsModal
* Disable French
* Styling updates to normalize text and accommodate other langs
* Add Portuguese Brazilian
* Fix Hotkey headers not being localized.
* Fix styling issue on models tag in Settings
* Fix Slider Styling to accommodate different languages
* Fix slider styling in light mode.
* Add German
* Add Italian
* Add Polish
* Update Italian
* Localized Frontend Build
* Updated RU Translations
* Fresh Build with updated RU changes
* Bug Fixes and Loc Updates
* Updated Frontend Build
* Fresh Build
Co-authored-by: Artur <83028930+netsvetaev@users.noreply.github.com>
* add example of using -from_file to read from a script
Addresses #1654, #473, #566, #1008 at least partially.
* fix bug in code example
* improve docs for !fetch and !replay
* enable rendering of images in GH WebUI
also fix indention in some bullet lists
Co-authored-by: mauwii <Mauwii@outlook.de>
When using the inpainting model, the following sequence of events
would cause a predictable crash:
1. Use unified canvas to outcrop a portion of the image.
2. Accept outcropped image and import into img2img
3. Try any img2img operation
This closes#1596.
The crash was:
```
operands could not be broadcast together with shapes (320,512) (512,576)
Traceback (most recent call last):
File "/data/lstein/InvokeAI/backend/invoke_ai_web_server.py", line 1125, in generate_images
self.generate.prompt2image(
File "/data/lstein/InvokeAI/ldm/generate.py", line 492, in prompt2image
results = generator.generate(
File "/data/lstein/InvokeAI/ldm/invoke/generator/base.py", line 98, in generate
image = make_image(x_T)
File "/data/lstein/InvokeAI/ldm/invoke/generator/omnibus.py", line 138, in make_image
return self.sample_to_image(samples)
File "/data/lstein/InvokeAI/ldm/invoke/generator/omnibus.py", line 173, in sample_to_image
corrected_result = super(Img2Img, self).repaste_and_color_correct(gen_result, self.pil_image, self.pil_mask, self.mask_blur_radius)
File "/data/lstein/InvokeAI/ldm/invoke/generator/base.py", line 148, in repaste_and_color_correct
mask_pixels = init_a_pixels * init_mask_pixels > 0
ValueError: operands could not be broadcast together with shapes (320,512) (512,576)
```
This error was caused by the image and its mask not being of identical
size due to the outcropping operation. The ultimate cause of this
error has something to do with different code paths being followed in
the `inpaint` vs the `omnibus` modules.
Since omnibus will be obsoleted by diffusers, I have chosen just to
work around the problem rather than track it down to its source. The
only ill effect is that color correction will not be applied to the
first image created by `img2img` after applying the outcrop and
immediately importing into the img2img canvas. Since the inpainting
model has less of a color drift problem than the standard model, this
is unlikely to be problematic.
* defer patchmatch loading
Because of the way that patchmatch was loaded early at import time, it
was impossible to turn off the attempted loading with --no-patchmatch.
In addition, the patchmatch loading messages appear early on during
initialization, interfering with ability to print out the version
cleanly when --version provided to invoke script.
This commit creates a thin wrapper class for patch_match that is only
loaded when needed, solving both problems.
* create a singleton patchmatch object for use in inpainting
This creates a thin wrapper to patchmatch which loads the module
on demand, respecting the global "trypatchmatch" option.
* address 2d round of issues in PR 2039 comments
* Patchmatch->PatchMatch and misc cleanup
* Correct asset link
Minor documentation fix to correct linked asset.
* fix switched graphics
also:
- add blanks before/after figure tag
(makes the screenshot also appear in github)
- use a table in inpainting example to have the pics side by side
Co-authored-by: mauwii <Mauwii@outlook.de>
* add --version to invoke.py arguments
This commit allows invoke.py to print out its name and version
number when given the --version argument. I had to move some
status messages around in order to make the output clean.
There is still an early message about initializing patchmatch
that interferes with a clean print of the version, and in fact the
--no-patchmatch argument is not doing anything. This will be the
subject of a subsequent PR.
* export APP_ID and APP_VERSION
Needed to support the web backend.
* (config) avoid failure when huggingface token is not set
it is not required for model download, and we are handling the
saving of the token during huggingface authentication phase elsewhere.
* (config) safely print to non-tty terminals where width can not be determined
* remove build-essentials after opencv is built
also remo unecesarry python3-opencv dependencie (its already in venv)
* use branch name as tag
* leave pip and setuptools on the preinstalled vers.
* Rename Argument from WORKDIR to APPDIR
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
* remove redundant code line
install.bat was copying the requirements file into the install folder
twice, causing an error message on the second try. This fixes the
issue.
* add further improvements to installer
- Windows version will unzip to have requirements.txt already in
the right location, to prevent problems when users try to run
the .bat script from within a mounted read-only zip file manager.
- Do not assume that "pip" is on the path in either the .bat or shell
versions of the update script.
* set workflow PR triggers to filter PR-types
- `review_requested`
- `ready_for_review`
* fail tests if draft pr
* add more types to test pr triggers
* remove unneeded condition
* readd condition
* leave PR-types default, only verify PRs to main
and fail for draft-PRs
* set types to cancel when converted to draft
* (config) handle huggingface token more gracefully
* (docs) document HuggingFace token requirement for Concepts
* (cli) deprecate the --(no)-interactive CLI flag
It was previously only used to skip the SD weights download, and therefore
the prompt for Huggingface token (the "interactive" part).
Now that we don't need a Huggingface token
to download the SD weights at all, we can replace this flag with
"--skip-sd-weights", to clearly describe its purpose
The `--(no)-interactive` flag still functions the same, but shows a deprecation message
* (cli) fix emergency_model_reconfigure argument parsing
* (config) fix installation issues on systems with non-UTF8 locale
Co-authored-by: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Before making a concept download request to HuggingFace, the concepts
library module now checks the concept name against a downloaded list
of all the concepts currently known to HuggingFace. If the requested
concept is not on the list, then no download request is made.
* add an argument that lets user specify folders to scan for weights
This PR adds a `--weight_folders` argument to invoke.py. Using
argparse, it adds a "weight_folders" attribute to the Args object, and
can be used like this:
```
'''test.py'''
from ldm.invoke.args import Args
args = Args().parse_args()
for folder in args.weight_folders:
print(folder)
```
Example output:
```
python test.py --weight_folders /tmp/weights /home/fred/invokeai/weights "./my folder with spaces/weight files"
/tmp/weights
/home/fred/invokeai/weights
./my folder with spaces/weight files
```
* change --weight_folders to --weight_dirs
* Auto-format frontend
* Update lint-frontend GA workflow node and checkout
* Fix linter error in ThemeChanger
* Add a `on: pull_request` to lint-frontend workflow
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
* update build scripts and dockerignore
updates to build and run script:
- read repository name
- include flavor in container name
- read arch via arch command
- use latest tag instead of arch
- don't bindmount `$HOME/.huggingface`
- make sure HUGGINGFACE_TOKEN is set
updates to .dockerignore
- include environment-and-requirements
- exclude binary_installer
- exclude docker-build
- exclude docs
* disable push and pr triggers of cloud image
also disable pushing.
This was decided since:
- it is not multiarch useable
- the default image is already cloud aproved
* integrate patchmatch in container
* pin verisons of recently introduced dependencies
* remove now unecesarry part from build.sh
move huggingface token to run script, so it can download missing models
* move GPU_FLAGS to run script
since not needed at build time
* update env.sh
- read REPOSITORY_NAME from env if available
- add comment to explain the intension of this file
- remove unecesarry exports
* get rid of repository_name_lc
* capitalize variables
* update INSTALL_DOCKER with new variables
* add comments pointing to the docs
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
1. Added a big fat warning to the Windows installer to tell user
to install Visual C++ redistributable.
2. Added a bit fat warning to the automated installer doc to
tell user the same thing.
3. Reordered entries on the table-of-contents sidebar for installation
to prioritize the most important docs.
4. Moved older installation documentation into deprecated folder.
5. Moved developer-specific installation documentation into the
developers folder.
* Correct timestep for img2img initial noise addition
* apply fix to inpaint and txt2img2img as well
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
- The invoke.py script now checks that the root (runtime) directory contains
the expected config/models.yaml file and if it doesn't exits with a helpful
error message about how to set the proper root.
- Formerly the script would fail with a "bad model" message and try to redownload
its models, which is not helpful in the case that the root is missing or
damaged.
- remove tests already performed in PR
- remove tests pointing to non existing files
- reduce steps to 20
This should decrease test time a lot and also "fix" failing mac tests.
I still recommend to invent why mac invoke takes so much longer!
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
Changed the hotkeys of Restore and Upscale from R and U to Shift R and Shift U. Users could accidentally press R and U to trigger these functions which can be annoying. Especially considering R is also a hotkey for Reset View in other tabs and it can become muscle memory.
* add logic for finding the root (runtime) directory
This commit fixes the root search logic to be as follows:
1) The `--root_dir` command line argument
2) The contents of environment variable INVOKEAI_ROOT
3) The VIRTUAL_ENV environment variable, plus '..'
4) $HOME/invokeai
(3) is the new feature. Since we are now recommending to install
InvokeAI and its dependencies into the .venv in the root directory,
this should be a reliable choice.
* make installer scripts more robust
This commits improves the installer .sh and .bat scripts in the following
ways:
1. They now handle folder/directory names containing spaces.
2. Pip will be installed into the .venv using the `ensurepip`
module.
This addresses issues identified by @vargol in Issue #1941
* add --prefer-binary option to pip install
* fix unset variable crash
* add patch level to zip file name
* Fix crash introduced in #1948
* Fix Prompt Placeholder Text Color
* Display Model Desc as tooltip in SiteHeader
This'll allow the user to quickly access info like activation token for that model if they set it in the description.
* Unified Canvas UI Beta
* Initial Test Build
* Make Snap Grid Hotkey Accessible Always
* Push dockerfile (#18)
* update build-container.yml
* add login step to build-container.yml
* update job name
* update matrix: add registry and platforms
also set latest only for cuda image
* quote string
* use latest for amd and cuda image
* separate images for cuda and amd
* change latest from auto to true
* configure_invoke -y instead of --interactive
* fix argument to --yes
* update matrix:
- use flavor instead of pip-requirements
- add flavor `cloud`
- add `dockerfile`
* introduce INVOKE_MODEL_RECONFIGURE
* add `--cap-add=sys_nice` to run.sh
* update Dockerfile: install wheel
* only have main branch in action again
* disable push of cloud image for now
since it still has it's own workflow, but PoC succeeded
* remove now untrue comments in top
* install pip, setuptools and wheel in sep. step
* add labels to the image
* remove doubled installation of wheel
This commit fixes the root search logic to be as follows:
1) The `--root_dir` command line argument
2) The contents of environment variable INVOKEAI_ROOT
3) The VIRTUAL_ENV environment variable, plus '..'
4) $HOME/invokeai
(3) is the new feature. Since we are now recommending to install
InvokeAI and its dependencies into the .venv in the root directory,
this should be a reliable choice.
The first few lines directed the user to run `python scripts/invoke.py`, which is not exactly correct anymore, and a holdover from previous versions.
Improves and clarifies the postscript messaging.
* updated Dockerfile
- use `python:3.10-slim` as baseimage
- separate builder and runtime stages again
- get rid of uneeded packages
- pin packages for persistence
- remove outdir from entrypoint since invoke.init is available in /data
- shrinked image size to <2GB
- way better security score than before
* small output update to build.sh and run.sh
* update matrix in build-container.yml
* remove branches from build-container.yml
- Using relative root addresses was causing problems when the
current working directory was changed after start time.
- This commit makes the root address absolute at start time, such
that changing the working directory later on doesn't break anything.
* partially working simple installer
* works on linux
* fix linux requirements files
* read root environment variable in right place
* fix cat invokeai.init in test workflows
* fix classical cp error in test-invoke-pip.yml
* respect --root argument now
* untested bat installers added
* windows install.bat now working
fix logic to find frontend files
* rename simple_install to "installer"
1. simple_install => 'installer'
2. source and binary install directories are removed
* enable update scripts to update requirements
- Also pin requirements to known working commits.
- This may be a breaking change; exercise with caution
- No functional testing performed yet!
* update docs and installation requirements
NOTE: This may be a breaking commit! Due to the way the installer
works, I have to push to a public branch in order to do full end-to-end
testing.
- Updated installation docs, removing binary and source installers and
substituting the "simple" unified installer.
- Pin requirements for the "http:" downloads to known working commits.
- Removed as much as possible the invoke-ai forks of others' repos.
* fix directory path for installer
* correct requirement/environment errors
* exclude zip files in .gitignore
* possible fix for dockerbuild
* ready for torture testing
- final Windows bat file tweaks
- copy environments-and-requirements to the runtime directory so that
the `update.sh` script can run.
This is not ideal, since we lose control over the
requirements. Better for the update script to pull the proper
updated requirements script from the repository.
* allow update.sh/update.bat to install arbitrary InvokeAI versions
- Can pass the zip file path to any InvokeAI release, branch, commit or tag,
and the installer will try to install it.
- Updated documentation
- Added Linux Python install hints.
* use binary installer's :err_exit function
* user diffusers 0.10.0
* added logic for CPPFLAGS on mac
* improve windows install documentation
- added information on a couple of gotchas I experienced during
windows installation, including DLL loading errors experienced
when Visual Studio C++ Redistributable was not present.
* tagged to pull from 2.2.4-rc1
- also fix error of shell window closing immediately if suitable
python not found
Co-authored-by: mauwii <Mauwii@outlook.de>
* attention maps saving to /tmp
* tidy up diffusers branch backporting of cross attention refactoring
* base64-encoding the attention maps image for generationResult
* cleanup/refactor conditioning.py
* attention maps and tokens being sent to web UI
* attention maps: restrict count to actual token count and improve robustness
* add argument type hint to image_to_dataURL function
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Co-authored-by: damian <git@damianstewart.com>
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
* add windows to test runners
* disable fail-fast for debugging
* re-enable login shell for conda workflow
also fix expression to exclude windows from run tests
* enable fail-fast again
* fix condition, pin runner verisons
* remove feature branch from push trigger
since already being triggered now via PR
* use gfpgan from pypi for windows
curious if this would fix the installation here as well
since worked for #1802
* unpin basicsr for windows
* for curiosity enabling testing for windows as well
* disable pip cache
since windows failed with a memory error now
but was working before it had a cache
* use matrix.github-env
* set platform specific root and outdir
* disable tests for windows since memory error
I guess the windows installation uses more space than linux
and for this they have less swap memory
In the event where no `init_mask` is given and `invert_mask` is set to True, the script will raise the following error:
```bash
AttributeError: 'NoneType' object has no attribute 'mode'
```
The new implementation will only run inversion when both variables are valid.
* update docker build (cloud) action with additional metadata, new labels
* (docker) also add aarch64 cloud build and remove arch suffix
* (docker) architecture suffix is needed for now
* (docker) don't build aarch64 for now
* add docker build optimized for size; do not copy models to image
useful for cloud deployments. attempts to utilize docker layer
caching as effectively as possible. also some quick tools to help with
building
* add workflow to build cloud img in ci
* push cloud image in addition to building
* (ci) also tag docker images with git SHA
* (docker) rework Makefile for easy cache population and local use
* support the new conda-less install; further optimize docker build
* (ci) clean up the build-cloud-img action
* improve the Makefile for local use
* move execution of invoke script from entrypoint to cmd, allows overriding the cmd if needed (e.g. in Runpod
* remove unnecessary copyright statements
* (docs) add a section on running InvokeAI in the cloud using Docker
* (docker) add patchmatch to the cloud image; improve build caching; simplify Makefile
* (docker) fix pip requirements path to use binary_installer directory
prompt token sequences begin with a "beginning-of-sequence" marker <bos> and end with a repeated "end-of-sequence" marker <eos> - to make a default prompt length of <bos> + 75 prompt tokens + <eos>. the .swap() code was failing to take the column for <bos> at index 0 into account. the changes here do that, and also add extra handling for a single <eos> (which may be redundant but which is included for completeness).
based on my understanding and some assumptions about how this all works, the reason .swap() nevertheless seemed to do the right thing, to some extent, is because over multiple steps the conditioning process in Stable Diffusion operates as a feedback loop. a change to token n-1 has flow-on effects to how the [1x4x64x64] latent tensor is modified by all the tokens after it, - and as the next step is processed, all the tokens before it as well. intuitively, a token's conditioning effects "echo" throughout the whole length of the prompt. so even though the token at n-1 was being edited when what the user actually wanted was to edit the token at n, it nevertheless still had some non-negligible effect, in roughly the right direction, often enough that it seemed like it was working properly.
- Pass command-line arguments through to invoke.py via the .bat and .sh scripts.
- Remove obsolete warning message from binary install.bat
- Make sure that current working directory matches where .bat file is installed
also "Macintosh" → "macOS" to improve "We Support macOS Properly And Not Halfassed Like Other OSS Projects" signalling
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
Several users have been trying to run InvokeAI on GTX 1650 and 1660
cards. They really can't because these cards don't work with
half-precision and only have 4-6GB of memory. Added a warning to
the docs (in two places) about this problem.
- Add Xcode installation instructions to source installer walkthrough
- Fix link to source installer page from installer overview
- If OSX install crashes, script will tell Mac users to go to the docs
to learn how to install Xcode
NB: if we remove the version from the zip file names, we can link
directly to assets in the latest GH release from documentation without
the need to keep the links updated
- The previous fix for the "install in Windows system directory" error would fail
if the path includes directories with spaces in them. This fixes that.
- In addition, addressing the same issue in source installer, although not
yet reported in wild.
- bat file changes to directory it lives in rather than user's current directory
- restore incorrect requirements and compiled Darwin requirements file
There was some old logic from before Unified Canvas which aborted generation when there was no currentImage.
If you have an image in the gallery, there is always a currentImage. But if gallery is empty, there is no currentImage. Generation would silently fail in this case.
We apparently never tested with an empty gallery and thus never ran into the issue. This removes this old and now-unused logic.
Some users were leaving whitespace at the end of their root
directories or ending them with a backslash. This caused the root
directory to become unusable. This removes whitespace and backslashes
from the end of the directory names.
Note that more needs to be done to cleanse the input, but for now
this will cover the cases we have seen so far in the wild.
Some users have been complaining that the CLI "freezes" for a while
before the invoke> prompt appears. I believe this is due to internet
delay while the concepts library names are downloaded by the autocompleter.
I have changed logic so that the concepts are downloaded the first time
the user types a < and tabs.
- Source installer provides more context for what it is doing, and
sends user to help/troubleshooting pages when something goes wrong.
- install.sh and install.bat are renamed to install.sh.in and install.bat.in
to discourage users from running them from within the
- Documentation updated
- make the warnings about patchmatch less redundant
- only warn about being unable to load concepts from Hugging Face
library once
- do not crash when unable to load concepts from Hugging Face
due to network connectivity issues
* Fixes inpainting + code cleanup
* Disable stage info in Inpainting Tab
* Mask Brush Preview now always at 0.5 opacity
The new mask is only visible properly at max opacity but at max opacity the brush preview becomes fully opaque blocking the view. So the mask brush preview no remains at 0.5 no matter what the Brush opacity is.
* Remove save button from Canvas Controls (cleanup)
* Implements invert mask
* Changes "Invert Mask" to "Preserve Masked Areas"
* Fixes (?) spacebar issues
* Patches redux-persist and redux-deep-persist with debounced persists
Our app changes redux state very, very often. As our undo/redo history grows, the calls to persist state start to take in the 100ms range, due to a the deep cloning of the history. This causes very noticeable performance lag.
The deep cloning is required because we need to blacklist certain items in redux from being persisted (e.g. the app's connection status).
Debouncing the whole process of persistence is a simple and effective solution. Unfortunately, `redux-persist` dropped `debounce` between v4 and v5, replacing it with `throttle`. `throttle`, instead of delaying the expensive action until a period of X ms of inactivity, simply ensures the action is executed at least every X ms. Of course, this does not fix our performance issue.
The patch is very simple. It adds a `debounce` argument - a number of milliseconds - and debounces `redux-persist`'s `update()` method (provided by `createPersistoid`) by that many ms.
Before this, I also tried writing a custom storage adapter for `redux-persist` to debounce the calls to `localStorage.setItem()`. While this worked and was far less invasive, it doesn't actually address the issue. It turns out `setItem()` is a very fast part of the process.
We use `redux-deep-persist` to simplify the `redux-persist` configuration, which can get complicated when you need to blacklist or whitelist deeply nested state. There is also a patch here for that library because it uses the same types as `redux-persist`.
Unfortunately, the last release of `redux-persist` used a package `flat-stream` which was malicious and has been removed from npm. The latest commits to `redux-persist` (about 1 year ago) do not build; we cannot use the master branch. And between the last release and last commit, the changes have all been breaking.
Patching this last release (about 3 years old at this point) directly is far simpler than attempting to fix the upstream library's master branch or figuring out an alternative to the malicious and now non-existent dependency.
* Adds debouncing
* Fixes AttributeError: 'dict' object has no attribute 'invert_mask'
* Updates package.json to use redux-persist patches
* Attempts to fix redux-persist debounce patch
* Fixes undo/redo
* Fixes invert mask
* Debounce > 300ms
* Limits history to 256 for each of undo and redo
* Canvas styling
* Hotkeys improvement
* Add Metadata To Viewer
* Increases CFG Scale max to 200
* Fix gallery width size for Outpainting
Also fixes the canvas resizing failing n fast pushes
* Fixes disappearing canvas grid lines
* Adds staging area
* Fixes "use all" not setting variationAmount
Now sets to 0 when the image had variations.
* Builds fresh bundle
* Outpainting tab loads to empty canvas instead of upload
* Fixes wonky canvas layer ordering & compositing
* Fixes error on inpainting paste back
`TypeError: 'float' object cannot be interpreted as an integer`
* Hides staging area outline on mouseover prev/next
* Fixes inpainting not doing img2img when no mask
* Fixes bbox not resizing in outpainting if partially off screen
* Fixes crashes during iterative outpaint. Still doesn't work correctly though.
* Fix iterative outpainting by restoring original images
* Moves image uploading to HTTP
- It all seems to work fine
- A lot of cleanup is still needed
- Logging needs to be added
- May need types to be reviewed
* Fixes: outpainting temp images show in gallery
* WIP refactor to unified canvas
* Removes console.log from redux-persist patch
* Initial unification of canvas
* Removes all references to split inpainting/outpainting canvas
* Add patchmatch and infill_method parameter to prompt2image (options are 'patchmatch' or 'tile').
* Fixes app after removing in/out-painting refs
* Rebases on dev, updates new env files w/ patchmatch
* Organises features/canvas
* Fixes bounding box ending up offscreen
* Organises features/canvas
* Stops unnecessary canvas rescales on gallery state change
* Fixes 2px layout shift on toggle canvas lock
* Clips lines drawn while canvas locked
When drawing with the locked canvas, if a brush stroke gets too close to the edge of the canvas and its stroke would extend past the edge of the canvas, the edge of that stroke will be seen after unlocking the canvas.
This could cause a problem if you unlock the canvas and now have a bunch of strokes just outside the init image area, which are far back in undo history and you cannot easily erase.
With this change, lines drawn while the canvas is locked get clipped to the initial image bbox, fixing this issue.
Additionally, the merge and save to gallery functions have been updated to respect the initial image bbox so they function how you'd expect.
* Fixes reset canvas view when locked
* Fixes send to buttons
* Fixes bounding box not being rounded to 64
* Abandons "inpainting" canvas lock
* Fixes save to gallery including empty area, adds download and copy image
* Fix Current Image display background going over image bounds
* Sets status immediately when clicking Invoke
* Adds hotkeys and refactors sharing of konva instances
Adds hotkeys to canvas. As part of this change, the access to konva instance objects was refactored:
Previously closure'd refs were used to indirectly get access to the konva instances outside of react components.
Now, a getter and setter function are used to provide access directly to the konva objects.
* Updates hotkeys
* Fixes canvas showing spinner on first load
Also adds good default canvas scale and positioning when no image is on it
* Fixes possible hang on MaskCompositer
* Improves behaviour when setting init canvas image/reset view
* Resets bounding box coords/dims when no image present
* Disables canvas actions which cannot be done during processing
* Adds useToastWatcher hook
- Dispatch an `addToast` action with standard Chakra toast options object to add a toast to the toastQueue
- The hook is called in App.tsx and just useEffect's w/ toastQueue as dependency to create the toasts
- So now you can add toasts anywhere you have access to `dispatch`, which includes middleware and thunks
- Adds first usage of this for the save image buttons in canvas
* Update Hotkey Info
Add missing tooltip hotkeys and update the hotkeys modal to reflect the new hotkeys for the Unified Canvas.
* Fix theme changer not displaying current theme on page refresh
* Fix tab count in hotkeys panel
* Unify Brush and Eraser Sizes
* Fix staging area display toggle not working
* Staging Area delete button is now red
So it doesnt feel blended into to the rest of them.
* Revert "Fix theme changer not displaying current theme on page refresh"
This reverts commit 903edfb803e743500242589ff093a8a8a0912726.
* Add arguments to use SSL to webserver
* Integrates #1487 - touch events
Need to add:
- Pinch zoom
- Touch-specific handling (some things aren't quite right)
* Refactors upload-related async thunks
- Now standard thunks instead of RTK createAsyncThunk()
- Adds toasts for all canvas upload-related actions
* Reorganises app file structure
* Fixes Canvas Auto Save to Gallery
* Fixes staging area outline
* Adds staging area hotkeys, disables gallery left/right when staging
* Fixes Use All Parameters
* Fix metadata viewer image url length when viewing intermediate
* Fixes intermediate images being tiny in txt2img/img2img
* Removes stale code
* Improves canvas status text and adds option to toggle debug info
* Fixes paste image to upload
* Adds model drop-down to site header
* Adds theme changer popover
* Fix missing key on ThemeChanger map
* Fixes stage position changing on zoom
* Hotkey Cleanup
- Viewer is now Z
- Canvas Move tool is V - sync with PS
- Removed some unused hotkeys
* Fix canvas resizing when both options and gallery are unpinned
* Implements thumbnails for gallery
- Thumbnails are saved whenever an image is saved, and when gallery requests images from server
- Thumbnails saved at original image aspect ratio with width of 128px as WEBP
- If the thumbnail property of an image is unavailable for whatever reason, the image's full size URL is used instead
* Saves thumbnails to separate thumbnails directory
* Thumbnail size = 256px
* Fix Lightbox Issues
* Disables canvas image saving functions when processing
* Fix index error on going past last image in Gallery
* WIP - Lightbox Fixes
Still need to fix the images not being centered on load when the image res changes
* Fixes another similar index error, simplifies logic
* Reworks canvas toolbar
* Fixes canvas toolbar upload button
* Cleans up IAICanvasStatusText
* Improves metadata handling, fixes#1450
- Removes model list from metadata
- Adds generation's specific model to metadata
- Displays full metadata in JSON viewer
* Gracefully handles corrupted images; fixes#1486
- App does not crash if corrupted image loaded
- Error is displayed in the UI console and CLI output if an image cannot be loaded
* Adds hotkey to reset canvas interaction state
If the canvas' interaction state (e.g. isMovingBoundingBox, isDrawing, etc) get stuck somehow, user can press Escape to reset the state.
* Removes stray console.log()
* Fixes bug causing gallery to close on context menu open
* Minor bugfixes
- When doing long-running canvas image exporting actions, display indeterminate progress bar
- Fix staging area image outline not displaying after committing/discarding results
* Removes unused imports
* Fixes repo root .gitignore ignoring frontend things
* Builds fresh bundle
* Styling updates
* Removes reasonsWhyNotReady
The popover doesn't play well with the button being disabled, and I don't think adds any value.
* Image gallery resize/style tweaks
* Styles buttons for clearing canvas history and mask
* First pass on Canvas options panel
* Fixes bug where discarding staged images results in loss of history
* Adds Save to Gallery button to staging toolbar
* Rearrange some canvas toolbar icons
Put brush stuff together and canvas movement stuff together
* Fix gallery maxwidth on unified canvas
* Update Layer hotkey display to UI
* Adds option to crop to bounding box on save
* Masking option tweaks
* Crop to Bounding Box > Save Box Region Only
* Adds clear temp folder
* Updates mask options popover behavior
* Builds fresh bundle
* Fix styling on alert modals
* Fix input checkbox styling being incorrect on light theme
* Styling fixes
* Improves gallery resize behaviour
* Cap gallery size on canvas tab so it doesnt overflow
* Fixes bug when postprocessing image with no metadata
* Adds IAIAlertDialog component
* Moves Loopback to app settings
* Fixes metadata viewer not showing metadata after refresh
Also adds Dream-style prompt to metadata
* Adds outpainting specific options
* Linting
* Fixes gallery width on lightbox, fixes gallery button expansion
* Builds fresh bundle
* Fix Lightbox images of different res not centering
* Update feature tooltip text
* Highlight mask icon when on mask layer
* Fix gallery not resizing correctly on open and close
* Add loopback to just img2img. Remove from settings.
* Fix to gallery resizing
* Removes Advanced checkbox, cleans up options panel for unified canvas
* Minor styling fixes to new options panel layout
* Styling Updates
* Adds infill method
* Tab Styling Fixes
* memoize outpainting options
* Fix unnecessary gallery re-renders
* Isolate Cursor Pos debug text on canvas to prevent rerenders
* Fixes missing postprocessed image metadata before refresh
* Builds fresh bundle
* Fix rerenders on model select
* Floating panel re-render fix
* Simplify fullscreen hotkey selector
* Add Training WIP Tab
* Adds Training icon
* Move full screen hotkey to floating to prevent tab rerenders
* Adds single-column gallery layout
* Fixes crash on cancel with intermediates enabled, fixes#1416
* Updates npm dependencies
* Fixes img2img attempting inpaint when init image has transparency
* Fixes missing threshold and perlin parameters in metadata viewer
* Renames "Threshold" > "Noise Threshold"
* Fixes postprocessing not being disabled when clicking use all
* Builds fresh bundle
* Adds color picker
* Lints & builds fresh bundle
* Fixes iterations being disabled when seed random & variations are off
* Un-floors cursor position
* Changes color picker preview to circles
* Fixes variation params not set correctly when recalled
* Fixes invoke hotkey not working in input fields
* Simplifies Accordion
Prep for adding reset buttons for each section
* Fixes mask brush preview color
* Committing color picker color changes tool to brush
* Color picker does not overwrite user-selected alpha
* Adds brush color alpha hotkey
* Lints
* Removes force_outpaint param
* Add inpaint size options to inpaint at a larger size than the actual inpaint image, then scale back down for recombination
* Bug fix for inpaint size
* Adds inpaint size (as scale bounding box) to UI
* Adds auto-scaling for inpaint size
* Improves scaled bbox display logic
* Fixes bug with clear mask and history
* Fixes shouldShowStagingImage not resetting to true on commit
* Builds fresh bundle
* Fixes canvas failing to scale on first run
* Builds fresh bundle
* Fixes unnecessary canvas scaling
* Adds gallery drag and drop to img2img/canvas
* Builds fresh bundle
* Fix desktop mode being broken with new versions of flaskwebgui
* Fixes canvas dimensions not setting on first load
* Builds fresh bundle
* stop crash on !import_models call on model inside rootdir
- addresses bug report #1546
* prevent "!switch state gets confused if model switching fails"
- If !switch were to fail on a particular model, then generate got
confused and wouldn't try again until you switch to a different working
model and back again.
- This commit fixes and closes#1547
* Revert "make the docstring more readable and improve the list_models logic"
This reverts commit 248068fe5d.
* fix model cache path
* also set fail-fast to it's default (true)
in this way the whole action fails if one job fails
this should unblock the runners!!!
* fix output path for Archive results
* disable checks for python 3.9
* Update-requirements and test-invoke-pip workflow (#1574)
* update requirements files
* update test-invoke-pip workflow
* move requirements-mkdocs.txt to docs folder (#1575)
* move requirements-mkdocs.txt to docs folder
* update copyright
* Fixes outpainting with resized inpaint size
* Interactive configuration (#1517)
* Update scripts/configure_invokeai.py
prevent crash if output exists
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
* implement changes requested by reviews
* default to correct root and output directory on Windows systems
- Previously the script was relying on the readline buffer editing
feature to set up the correct default. But this feature doesn't
exist on windows.
- This commit detects when user typed return with an empty directory
value and replaces with the default directory.
* improved readability of directory choices
* Update scripts/configure_invokeai.py
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
* better error reporting at startup
- If user tries to run the script outside of the repo or runtime directory,
a more informative message will appear explaining the problem.
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
* Embedding merging (#1526)
* add whole <style token> to vocab for concept library embeddings
* add ability to load multiple concept .bin files
* make --log_tokenization respect custom tokens
* start working on concept downloading system
* preliminary support for dynamic loading and merging of multiple embedded models
- The embedding_manager is now enhanced with ldm.invoke.concepts_lib,
which handles dynamic downloading and caching of embedded models from
the Hugging Face concepts library (https://huggingface.co/sd-concepts-library)
- Downloading of a embedded model is triggered by the presence of one or more
<concept> tags in the prompt.
- Once the embedded model is downloaded, its trigger phrase will be loaded
into the embedding manager and the prompt's <concept> tag will be replaced
with the <trigger_phrase>
- The downloaded model stays on disk for fast loading later.
- The CLI autocomplete will complete partial <concept> tags for you. Type a
'<' and hit tab to get all ~700 concepts.
BUGS AND LIMITATIONS:
- MODEL NAME VS TRIGGER PHRASE
You must use the name of the concept embed model from the SD
library, and not the trigger phrase itself. Usually these are the
same, but not always. For example, the model named "hoi4-leaders"
corresponds to the trigger "<HOI4-Leader>"
One reason for this design choice is that there is no apparent
constraint on the uniqueness of the trigger phrases and one trigger
phrase may map onto multiple models. So we use the model name
instead.
The second reason is that there is no way I know of to search
Hugging Face for models with certain trigger phrases. So we'd have
to download all 700 models to index the phrases.
The problem this presents is that this may confuse users, who will
want to reuse prompts from distributions that use the trigger phrase
directly. Usually this will work, but not always.
- WON'T WORK ON A FIREWALLED SYSTEM
If the host running IAI has no internet connection, it can't
download the concept libraries. I will add a script that allows
users to preload a list of concept models.
- BUG IN PROMPT REPLACEMENT WHEN MODEL NOT FOUND
There's a small bug that occurs when the user provides an invalid
model name. The <concept> gets replaced with <None> in the prompt.
* fix loading .pt embeddings; allow multi-vector embeddings; warn on dupes
* simplify replacement logic and remove cuda assumption
* download list of concepts from hugging face
* remove misleading customization of '*' placeholder
the existing code as-is did not do anything; unclear what it was supposed to do.
the obvious alternative -- setting using 'placeholder_strings' instead of
'placeholder_tokens' to match model.params.personalization_config.params.placeholder_strings --
caused a crash. i think this is because the passed string also needed to be handed over
on init of the PersonalizedBase as the 'placeholder_token' argument.
this is weird config dict magic and i don't want to touch it. put a
breakpoint in personalzied.py line 116 (top of PersonalizedBase.__init__) if
you want to have a crack at it yourself.
* address all the issues raised by damian0815 in review of PR #1526
* actually resize the token_embeddings
* multiple improvements to the concept loader based on code reviews
1. Activated the --embedding_directory option (alias --embedding_path)
to load a single embedding or an entire directory of embeddings at
startup time.
2. Can turn off automatic loading of embeddings using --no-embeddings.
3. Embedding checkpoints are scanned with the pickle scanner.
4. More informative error messages when a concept can't be loaded due
either to a 404 not found error or a network error.
* autocomplete terms end with ">" now
* fix startup error and network unreachable
1. If the .invokeai file does not contain the --root and --outdir options,
invoke.py will now fix it.
2. Catch and handle network problems when downloading hugging face textual
inversion concepts.
* fix misformatted error string
Co-authored-by: Damian Stewart <d@damianstewart.com>
* model_cache.py: fix list_models
Signed-off-by: devops117 <55235206+devops117@users.noreply.github.com>
* add statement of values (#1584)
* this adds the Statement of Values
Google doc source = https://docs.google.com/document/d/1-PrUKDJcxy8OyNGc8CyiHhv2VgLvjt7LRGlEpbg1nmQ/edit?usp=sharing
* Fix heading
* Update InvokeAI_Statement_of_Values.md
* Update InvokeAI_Statement_of_Values.md
* Update InvokeAI_Statement_of_Values.md
* Update InvokeAI_Statement_of_Values.md
* Update InvokeAI_Statement_of_Values.md
* add keturn and mauwii to the team member list
* Fix punctuation
* this adds the Statement of Values
Google doc source = https://docs.google.com/document/d/1-PrUKDJcxy8OyNGc8CyiHhv2VgLvjt7LRGlEpbg1nmQ/edit?usp=sharing
* add keturn and mauwii to the team member list
* fix formating
- make sub bullets use * (decide to all use - or *)
- indent sub bullets
Sorry, first only looked at the code version and found this only after
looking at the markdown rendered version
* use multiparagraph numbered sections
* Break up Statement Of Values as per comments on #1584
* remove duplicated word, reduce vagueness
it's important not to overstate how many artists we are consulting.
* fix typo (sorry blessedcoolant)
Co-authored-by: mauwii <Mauwii@outlook.de>
Co-authored-by: damian <git@damianstewart.com>
* update dockerfile (#1551)
* update dockerfile
* remove not existing file from .dockerignore
* remove bloat and unecesary step
also use --no-cache-dir for pip install
image is now close to 2GB
* make Dockerfile a variable
* set base image to `ubuntu:22.10`
* add build-essential
* link outputs folder for persistence
* update tag variable
* update docs
* fix not customizeable build args, add reqs output
* !model_import autocompletes in ROOTDIR
* Adds psychedelicious to statement of values signature (#1602)
* add a --no-patchmatch option to disable patchmatch loading (#1598)
This feature was added to prevent the CI Macintosh tests from erroring
out when patchmatch is unable to retrieve its shared library from
github assets.
* Fix#1599 by relaxing the `match_trigger` regex (#1601)
* Fix#1599 by relaxing the `match_trigger` regex
Also simplify logic and reduce duplication.
* restrict trigger regex again (but not so far)
* make concepts library work with Web UI
This PR makes it possible to include a Hugging Face concepts library
<style-or-subject-trigger> in the WebUI prompt. The metadata seems
to be correctly handled.
* documentation enhancements (#1603)
- Add documentation for the Hugging Face concepts library and TI embedding.
- Fixup index.md to point to each of the feature documentation files,
including ones that are pending.
* tweak setup and environment files for linux & pypatchmatch (#1580)
* tweak setup and environment files for linux & pypatchmatch
- Downgrade python requirements to 3.9 because 3.10 is not supported
on Ubuntu 20.04 LTS (widely-used distro)
- Use our github pypatchmatch 0.1.3 in order to install Makefile
where it needs to be.
- Restored "-e ." as the last install step on pip installs. Hopefully
this will not trigger the high-CPU hang we've previously experienced.
* keep windows on basicsr 1.4.1
* keep windows on basicsr 1.4.1
* bump pypatchmatch requirement to 0.1.4
- This brings in a version of pypatchmatch that will gracefully
handle internet connection not available at startup time.
- Also refactors and simplifies the handling of gfpgan's basicsr requirement
across various platforms.
* revert to older version of list_models() (#1611)
This restores the correct behavior of list_models() and quenches
the bug of list_models() returning a single model entry named "name".
I have not investigated what was wrong with the new version, but I
think it may have to do with changes to the behavior in dict.update()
* Fixes for #1604 (#1605)
* Converts ESRGAN image input to RGB
- Also adds typing for image input.
- Partially resolves#1604
* ensure there are unmasked pixels before color matching
Co-authored-by: Kyle Schouviller <kyle0654@hotmail.com>
* update index.md (#1609)
- comment out non existing link
- fix indention
- add seperator between feature categories
* Debloat-docker (#1612)
* debloat Dockerfile
- less options more but more userfriendly
- better Entrypoint to simulate CLI usage
- without command the container still starts the web-host
* debloat build.sh
* better syntax in run.sh
* update Docker docs
- fix description of VOLUMENAME
- update run script example to reflect new entrypoint
* Test installer (#1618)
* test linux install
* try removing http from parsed requirements
* pip install confirmed working on linux
* ready for linux testing
- rebuilt py3.10-linux-x86_64-cuda-reqs.txt to include pypatchmatch
dependency.
- point install.sh and install.bat to test-installer branch.
* Updates MPS reqs
* detect broken readline history files
* fix download.pytorch.org URL
* Test installer (Win 11) (#1620)
Co-authored-by: Cyrus Chan <cyruswkc@hku.hk>
* Test installer (MacOS 13.0.1 w/ torch==1.12.0) (#1621)
* Test installer (Win 11)
* Test installer (MacOS 13.0.1 w/ torch==1.12.0)
Co-authored-by: Cyrus Chan <cyruswkc@hku.hk>
* change sourceball to development for testing
* Test installer (MacOS 13.0.1 w/ torch==1.12.1 & torchvision==1.13.1) (#1622)
* Test installer (Win 11)
* Test installer (MacOS 13.0.1 w/ torch==1.12.0)
* Test installer (MacOS 13.0.1 w/ torch==1.12.1 & torchvision==1.13.1)
Co-authored-by: Cyrus Chan <cyruswkc@hku.hk>
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Co-authored-by: Cyrus Chan <82143712+cyruschan360@users.noreply.github.com>
Co-authored-by: Cyrus Chan <cyruswkc@hku.hk>
* 2.2 Doc Updates (#1589)
* Unified Canvas Docs & Assets
Unified Canvas draft
Advanced Tools Updates
Doc Updates (lstein feedback)
* copy edits to Unified Canvas docs
- consistent capitalisation and feature naming
- more intimate address (replace "the user" with "you") for improved User
Engagement(tm)
- grammatical massaging and *poesie*
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
Co-authored-by: damian <git@damianstewart.com>
* include a step after config to `cat ~/.invokeai` (#1629)
* disable patchmatch in CI actions (#1626)
* disable patchmatch in CI actions
* fix indention
* replace tab with spaces
Co-authored-by: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Co-authored-by: mauwii <Mauwii@outlook.de>
* Fix installer script for macOS. (#1630)
* refer to the platform as 'osx' instead of 'mac', otherwise the
composed URL to micromamba is wrong.
* move the `-O` option to `tar` to be grouped with the other tar flags
to avoid the `-O` being interpreted as something to unarchive.
* Removes symlinked environment.yaml (#1631)
Was unintentionally added in #1621
* Fix inpainting with iterations (#1635)
* fix error when inpainting using runwayml inpainting model (#1634)
- error was "Omnibus object has no attribute pil_image"
- closes#1596
* add k_dpmpp_2_a and k_dpmpp_2 solvers options (#1389)
* add k_dpmpp_2_a and k_dpmpp_2 solvers options
* update frontend
Co-authored-by: Victor <victorca25@users.noreply.github.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
* add .editorconfig (#1636)
* Web UI 2.2 bugfixes (#1572)
* Fixes bug preventing multiple images from being generated
* Fixes valid seam strength value range
* Update Delete Alert Text
Indicates to the user that images are not permanently deleted.
* Fixes left/right arrows not working on gallery
* Fixes initial image on load erroneously set to a user uploaded image
Should be a result gallery image.
* Lightbox Fixes
- Lightbox is now a button in the current image buttons
- Lightbox is also now available in the gallery context menu
- Lightbox zoom issues fixed
- Lightbox has a fade in animation.
* Fix image display wrapper in current preview not overflow bounds
* Revert "Fix image display wrapper in current preview not overflow bounds"
This reverts commit 5511c82714dbf1d1999d64e8bc357bafa34ddf37.
* Change Staging Area discard icon from Bin to X
* Expose Snap Threshold and Move Snap Settings to BBox Panel
* Changes img2img strength default to 0.75
* Fixes drawing triggering when mouse enters canvas w/ button down
When we only supported inpainting and no zoom, this was useful. It allowed the cursor to leave the canvas (which was easy to do given the limited canvas dimensions) and without losing the "I am drawing" state.
With a zoomable canvas this is no longer as useful.
Additionally, we have more popovers and tools (like the color pickers) which result in unexpected brush strokes. This fixes that issue.
* Revert "Expose Snap Threshold and Move Snap Settings to BBox Panel"
We will handle this a bit differently - by allowing the grid origin to be moved. I will dig in at some point.
This reverts commit 33c92ecf4da724c2f17d9d91c7ea31a43a2f6deb.
* Adds Limit Strokes to Box
* Adds fill bounding box button
* Adds erase bounding box button
* Changes Staging area discard icon to match others
* Fixes right click breaking move tool
* Fixes brush preview visibility issue with "darken outside box"
* Fixes history bugs with addFillRect, addEraseRect, and other actions
* Adds missing `key`
* Fixes postprocessing being applied to canvas generations
* Fixes bbox not getting scaled in various situations
* Fixes staging area show image toggle not resetting on accept/discard
* Locks down canvas while generating/staging
* Fixes move tool breaking when canvas loses focus during move/transform
* Hides cursor when restrict strokes is on and mouse outside bbox
* Lints
* Builds fresh bundle
* Fix overlapping hotkey for Fill Bounding Box
* Build Fresh Bundle
* Fixes bug with mask and bbox overlay
* Builds fresh bundle
Co-authored-by: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
* disable NSFW checker loading during the CI tests (#1641)
* disable NSFW checker loading during the CI tests
The NSFW filter apparently causes invoke.py to crash during CI testing,
possibly due to out of memory errors. This workaround disables NSFW
model loading.
* doc change
* fix formatting errors in yml files
* Configure the NSFW checker at install time with default on (#1624)
* configure the NSFW checker at install time with default on
1. Changes the --safety_checker argument to --nsfw_checker and
--no-nsfw_checker. The original argument is recognized for backward
compatibility.
2. The configure script asks users whether to enable the checker
(default yes). Also offers users ability to select default sampler and
number of generation steps.
3.Enables the pasting of the caution icon on blurred images when
InvokeAI is installed into the package directory.
4. Adds documentation for the NSFW checker, including caveats about
accuracy, memory requirements, and intermediate image dispaly.
* use better fitting icon
* NSFW defaults false for testing
* set default back to nsfw active
Co-authored-by: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Co-authored-by: mauwii <Mauwii@outlook.de>
Signed-off-by: devops117 <55235206+devops117@users.noreply.github.com>
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Co-authored-by: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Co-authored-by: Kyle Schouviller <kyle0654@hotmail.com>
Co-authored-by: javl <mail@jaspervanloenen.com>
Co-authored-by: Kent Keirsey <31807370+hipsterusername@users.noreply.github.com>
Co-authored-by: mauwii <Mauwii@outlook.de>
Co-authored-by: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Co-authored-by: Damian Stewart <d@damianstewart.com>
Co-authored-by: DevOps117 <55235206+devops117@users.noreply.github.com>
Co-authored-by: damian <git@damianstewart.com>
Co-authored-by: Damian Stewart <null@damianstewart.com>
Co-authored-by: Cyrus Chan <82143712+cyruschan360@users.noreply.github.com>
Co-authored-by: Cyrus Chan <cyruswkc@hku.hk>
Co-authored-by: Andre LaBranche <dre@mac.com>
Co-authored-by: victorca25 <41912303+victorca25@users.noreply.github.com>
Co-authored-by: Victor <victorca25@users.noreply.github.com>
Squashed commit of the following:
commit 9a1fe8e7fb
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 12 17:07:40 2022 +0000
swap in release URLs for installers
commit ff56f5251b
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 12 17:03:21 2022 +0000
fix up bad unicode chars in invoke.py
commit ed943bd6c7
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 12 16:05:45 2022 +0000
outcrop improvements, hand-added
commit 7ad2355b1d
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 12 15:14:33 2022 +0000
documentation fixes
commit 66c920fc19
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 16:49:25 2022 -0500
Revert "Resize hires as an image"
This reverts commit d05b1b3544.
commit 3fc5cb09f8
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 12 12:43:17 2022 +0000
fix incorrect link in install
commit 1345ec77ab
Author: tildebyte <337875+tildebyte@users.noreply.github.com>
Date: Sun Nov 6 19:07:31 2022 -0500
toil(repo): add tildebyte as owner of installer/ directory
commit b116715490
Author: Kyle Schouviller <kyle0654@hotmail.com>
Date: Thu Nov 10 21:43:56 2022 -0800
Fix performance issue introduced by torch cuda cache clear during generation
commit fa3670270e
Author: mauwii <Mauwii@outlook.de>
Date: Fri Nov 11 12:42:03 2022 +0100
small update to dockers huggingface section
commit c304250ef6
Author: mauwii <Mauwii@outlook.de>
Date: Fri Nov 11 12:19:27 2022 +0100
fix format and Link in INSTALL_INVOKE.md
commit 802ce5dde5
Author: mauwii <Mauwii@outlook.de>
Date: Fri Nov 11 11:17:49 2022 +0100
small fixex to format and a link in INSTALL_MANUAL
commit 311ee320ec
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 11 07:23:35 2022 +0000
ignore installer intermediate files
commit e9df17b374
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 11 07:19:25 2022 +0000
fix backslash-related syntax error
commit 061fb4ef00
Merge: 52be0d234095acd1
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 11 06:50:04 2022 +0000
Merge branch 'release-candidate-2-1-3' of github.com:/invoke-ai/InvokeAI into release-candidate-2-1-3
commit 52be0d2396
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 11 06:49:45 2022 +0000
add WindowsLongFileName batfile to source installer
commit 4095acd10e
Author: mauwii <Mauwii@outlook.de>
Date: Fri Nov 11 07:05:17 2022 +0100
Doc Updates
A lot of re-formating of new Installation Docs
also some content updates/corrections
commit 201eb22d76
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 11 04:41:02 2022 +0000
prevent two models from being marked default in models.yaml
commit 17ab982200
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 11 03:56:54 2022 +0000
installers download branch HEAD not tag
commit a04965b0e9
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 11 03:48:21 2022 +0000
improve messaging during installation process
commit 0b529f0c57
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 15:22:32 2022 +0000
enable outcropping of random JPG/PNG images
- Works best with runwayML inpainting model
- Numerous code changes required to propagate seed to final metadata.
Original code predicated on the image being generated within InvokeAI.
commit 6f9f848345
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 17:27:42 2022 +0000
enhance outcropping with ability to direct contents of new regions
- When outcropping an image you can now add a `--new_prompt` option, to specify
a new prompt to be used instead of the original one used to generate the image.
- Similarly you can provide a new seed using `--seed` (or `-S`). A seed of zero
will pick one randomly.
- This PR also fixes the crash that happened when trying to outcrop an image
that does not contain InvokeAI metadata.
commit 918c1589ef
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 20:16:47 2022 +0000
fix#1402
commit 116415b3fc
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 21:27:25 2022 +0000
fix invoke.py crash if no models.yaml file present
- Script will now offer the user the ability to create a
minimal models.yaml and then gracefully exit.
- Closes#1420
commit b4b6eabaac
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 16:49:25 2022 -0500
Revert "Log strength with hires"
This reverts commit 82d4904c07.
commit 4ef1f4a854
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 20:01:49 2022 +0000
remove temporary directory from repo
commit 510fc4ebaa
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 19:59:03 2022 +0000
remove -e from clipseg load in installer
commit a20914434b
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 19:37:07 2022 +0000
change clipseg repo branch to avoid clipseg not found error
commit 0d134195fd
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 18:39:29 2022 +0000
update repo URL to point to rc
commit 649d8c8573
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 18:13:28 2022 +0000
integrate tildebyte installer
commit a358d370a0
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 17:48:14 2022 +0000
add @tildebyte compiled pip installer
commit 94a9033c4f
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 14:52:00 2022 +0000
ignore source installer zip files
commit 18a947c503
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 14:46:36 2022 +0000
documentation and environment file fixes
- Have clarified the relationship between the @tildebyte and @cmdr2 installers;
However, @tildebyte installer merge is still a WIP due to conflicts over
such things as `invoke.sh`.
- Rechristened 1click installer as "source" installer. @tildebyte installer will be
"the" installer. (We'll see which one generates the least support requests and
maintenance work.)
- Sync'd `environment-mac.yml` with `development`. The former was failing with a
taming-transformers error as per https://discord.com/channels/@me/1037201214154231899/1040060947378749460
commit a23b031895
Author: Mike DiGiovanni <vinblau@gmail.com>
Date: Wed Nov 9 16:44:59 2022 -0500
Fixes typos in README.md
commit 23af68c7d7
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 07:02:27 2022 -0500
downgrade win installs to basicsr==1.4.1
commit e258beeb51
Merge: 7460c069e481bfac
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 06:37:45 2022 -0500
Merge branch 'release-candidate-2-1-3' of github.com:invoke-ai/InvokeAI into release-candidate-2-1-3
commit 7460c069b8
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 06:36:48 2022 -0500
remove --prefer-binary from requirements-base.txt
It appears that some versions of pip do not recognize this option
when it appears in the requirements file. Did not explore this further
but recommend --prefer-binary in the manual install instructions on
the command line.
commit e481bfac61
Merge: 5040747cd1ab65a4
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 11:21:56 2022 +0000
Merge branch 'release-candidate-2-1-3' of github.com:/invoke-ai/InvokeAI into release-candidate-2-1-3
commit 5040747c67
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 10 11:21:43 2022 +0000
fix windows install instructions & bat file
commit d1ab65a431
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 10 07:18:59 2022 +0100
update WEBUIHOTKEYS.md
commit af4ee7feb8
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 10 06:33:49 2022 +0100
update INSTALL_DOCKER.md
commit 764fb29ade
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 10 06:30:15 2022 +0100
fix formatting in INSTALL.md
commit 1014d3ba44
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 10 06:29:14 2022 +0100
fix build.sh invokeai_conda_env_file default value
commit 40a48aca88
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 10 05:25:30 2022 +0100
fix environment-mac.yml
moved taming-transformers-rom1504 to pip dependencies
commit 92abc00f16
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 10 05:19:52 2022 +0100
fix test-invoke-conda
- copy required conda environment yaml
- use environment.yml
- I use cp instead of ln since would be compatible for windows runners
commit a5719aabf8
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 10 04:14:35 2022 +0100
update Dockerfile
- link environment.yml from new environemnts path
- change default conda_env_file
- quote all variables to avoid splitting
- also remove paths from conda-env-files in build-container.yml
commit 44a18511fa
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 20:51:06 2022 +0000
update paths in container build workflow
commit b850dbadaf
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 20:16:57 2022 +0000
finished reorganization of install docs
commit 9ef8b944d5
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 18:50:58 2022 +0000
tweaks to manual install documentation
--prefer-binary is an iffy option in the requirements file. It isn't
supported by some versions of pip, so I removed it from
requirements-base.txt and inserted it into the manual install
instructions where it seems to do what it is supposed to.
commit efc5a98488
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 18:20:03 2022 +0000
manual installation documentation tested on Linux
commit 1417c87928
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 17:37:06 2022 +0000
change name of requirements.txt to avoid confusion
commit 2dd6fc2b93
Merge: 2221361271ee44a8
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 17:26:24 2022 +0000
Merge branch 'release-candidate-2-1-3' of github.com:/invoke-ai/InvokeAI into release-candidate-2-1-3
commit 22213612a0
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 17:25:59 2022 +0000
directory cleanup; working on install docs
commit 71ee44a827
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 02:07:13 2022 +0000
prevent crash when switching to an invalid model
commit b17ca0a5e7
Author: damian0815 <null@damianstewart.com>
Date: Tue Nov 8 14:28:38 2022 +0100
don't suppress exceptions when doing cross-attention control
commit 71bbfe4a1a
Author: damian0815 <null@damianstewart.com>
Date: Tue Nov 8 12:59:34 2022 +0100
Fix#1362 by improving VRAM usage patterns when doing .swap()
commit ef3f7a26e242b73c2beb0195c7fd8f654ef47f55
Author: damian0815 <null@damianstewart.com>
Date: Tue Nov 8 12:18:37 2022 +0100
remove log spam
commit 7189d649622d4668b120b0dd278388ad672142c4
Author: damian0815 <null@damianstewart.com>
Date: Tue Nov 8 12:10:28 2022 +0100
change the way saved slicing strategy is applied
commit 01c40f751ab72955140165c16f95ae411732265b
Author: damian0815 <null@damianstewart.com>
Date: Tue Nov 8 12:04:43 2022 +0100
fix slicing_strategy_getter callsite
commit f8cfe25150a346958903316bc710737d99839923
Author: damian0815 <null@damianstewart.com>
Date: Tue Nov 8 11:56:22 2022 +0100
cleanup, consistent dim=0 also tested
commit 5bf9b1e890d48e962afd4a668a219b68271e5dc1
Author: damian0815 <null@damianstewart.com>
Date: Tue Nov 8 11:34:09 2022 +0100
refactored context, tested with non-sliced cross attention control
commit d58a46e39bf562e7459290d2444256e8c08ad0b6
Author: damian0815 <null@damianstewart.com>
Date: Sun Nov 6 00:41:52 2022 +0100
cleanup
commit 7e2c658b4c06fe239311b65b9bb16fa3adec7fd7
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:57:31 2022 +0100
disable logs
commit 20ee89d93841b070738b3d8a4385c93b097d92eb
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:36:58 2022 +0100
slice saved attention if necessary
commit 0a7684a22c880ec0f48cc22bfed4526358f71546
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:32:38 2022 +0100
raise instead of asserting
commit 7083104c7f3a0d8fd96e94a2f391de50a3c942e4
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:31:00 2022 +0100
store dim when saving slices
commit f7c0808ed383ec1dc70645288a798ed2aa4fa85c
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:27:16 2022 +0100
don't retry on exception
commit 749a721e939b3fe7c1741e7998dab6bd2c85a0cb
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:24:50 2022 +0100
stuff
commit 032ab90e9533be8726301ec91b97137e2aadef9a
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:20:17 2022 +0100
more logging
commit 3dc34b387f033482305360e605809d95a40bf6f8
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:16:47 2022 +0100
logs
commit 901c4c1aa4b9bcef695a6551867ec8149e6e6a93
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:12:39 2022 +0100
actually set save_slicing_strategy to True
commit f780e0a0a7c6b6a3db320891064da82589358c8a
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 22:10:35 2022 +0100
store slicing strategy
commit 93bb6d566fd18c5c69ef7dacc8f74ba2cf671cb7
Author: damian <git@damianstewart.com>
Date: Sat Nov 5 20:43:48 2022 +0100
still not it
commit 5e3a9541f8ae00bde524046963910323e20c40b7
Author: damian <git@damianstewart.com>
Date: Sat Nov 5 17:20:02 2022 +0100
wip offloading attention slices on-demand
commit 4c2966aa856b6f3b446216da3619ae931552ef08
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 15:47:40 2022 +0100
pre-emptive offloading, idk if it works
commit 572576755e9f0a878d38e8173e485126c0efbefb
Author: root <you@example.com>
Date: Sat Nov 5 11:25:32 2022 +0000
push attention slices to cpu. slow but saves memory.
commit b57c83a68f2ac03976ebc89ce2ff03812d6d185f
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 12:04:22 2022 +0100
verbose logging
commit 3a5dae116f110a96585d9eb71d713b5ed2bc3d2b
Author: damian0815 <null@damianstewart.com>
Date: Sat Nov 5 11:50:48 2022 +0100
wip fixing mem strategy crash (4 test on runpod)
commit 3cf237db5fae0c7b0b4cc3c47c81830bdb2ae7de
Author: damian0815 <null@damianstewart.com>
Date: Fri Nov 4 09:02:40 2022 +0100
wip, only works on cuda
commit 5702271991
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 14:09:36 2022 +0000
speculative reorganization of the requirements & environment files
- This is only a test!
- The various environment*.yml and requirements*.txt files have all
been moved into a directory named "environments-and-requirements".
- The idea is to clean up our root directory so that the github home
page is tidy.
- The manual install instructions will start with the instructions to
create a symbolic link from environment.yml to the appropriate file
for OS and GPU.
- The 1-click installers have been updated to accommodate this change.
commit 10781e7dc4
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 9 01:59:45 2022 +0000
refactoring requirements
commit 099d1157c5
Author: mauwii <Mauwii@outlook.de>
Date: Wed Nov 9 00:16:18 2022 +0100
better way to make sure if conda is useable
commit ab825bf7ee
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 22:05:33 2022 +0000
add back --prefer-binaries to requirements
commit 10cfeb5ada
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 8 22:27:19 2022 +0100
add quotes to set and use `$environment_file`
commit e97515d045
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 8 22:24:21 2022 +0100
set environment file for conda update
commit 0f04bc5789
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 8 22:21:25 2022 +0100
use conda env update
commit 3f74aabecd
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 8 22:20:44 2022 +0100
use command instead of hash
commit b1a99a51b7
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 14:44:44 2022 -0500
remove --global git config from 1-click installers
commit 8004f8a6d9
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Nov 7 09:07:20 2022 -0500
Revert "Use array slicing to calc ddim timesteps"
This reverts commit 1f0c5b4cf1.
commit ff8ff2212a
Merge: 8e5363cd636620b1
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 14:01:40 2022 +0000
add initfile support from PR #1386
commit 8e5363cd83
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 13:26:18 2022 +0000
move 'installer/' to '1-click-installer' to make room for tildebyte installer
commit 1450779146
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 12:56:36 2022 +0000
update branch for installer to pull against
commit 8cd5d95b8a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 05:30:20 2022 +0000
move all models into subdirectories of ./models
- this required an update to the invoke-ai fork of gfpgan
- simultaneously reverted consolidation of environment and
requirements files, as their presence in a directory
triggered setup.py to try to install a sub-package.
commit abd6407394
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 03:52:46 2022 +0000
leave a copy of environment-cuda.yml at top level
- named it environment.yml
- need to avoid a big change for users and breaking older support
instructions.
commit 734dacfbe9
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 03:50:07 2022 +0000
consolidate environment files
- starting to remove unneeded entries and pins
- no longer require -e in front of github dependencies
- update setup.py with release number
- update manual installation instructions
commit 636620b1d5
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 8 03:26:16 2022 +0000
change initfile to ~/.invokeai
- adjust documentation
- also fix 'clipseg_models' to 'clipseg', which seems to be working now
commit 1fe41146f0
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 5 14:28:01 2022 -0400
add support for an initialization file, invokeai.init
- Place preferred startup command switches in a file named
"invokeai.init". The file can consist of a single line of switches
such as "--web --steps=28", a series of switches on each
line, or any combination of the two.
Example:
```
--web
--host=0.0.0.0
--steps=28
--grid
-f 0.6 -C 11.0 -A k_euler_a
```
- The following options, which were previously only available within
the CLI, are now available on the command line as well:
--steps
--strength
--cfg_scale
--width
--height
--fit
commit 2ad6ef355a
Merge: 865502ee8b47c829
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Nov 6 18:08:36 2022 +0000
update discord link
commit 865502ee4f
Author: mauwii <Mauwii@outlook.de>
Date: Sun Nov 6 18:00:16 2022 +0100
update changelog
commit c7984f3299
Author: mauwii <Mauwii@outlook.de>
Date: Sun Nov 6 17:07:27 2022 +0100
update TROUBLESHOOT.md
commit 7f150ed833
Author: mauwii <Mauwii@outlook.de>
Date: Sun Nov 6 16:56:58 2022 +0100
remove `:`from headlines in CONTRIBUTORS.md
commit badf4e256c
Author: mauwii <Mauwii@outlook.de>
Date: Sun Nov 6 16:56:37 2022 +0100
enable navigation tabs
Since the docs are growing, this way they look cleaner
commit e64c60bbb3
Author: mauwii <Mauwii@outlook.de>
Date: Sun Nov 6 16:18:59 2022 +0100
remove preflight checks from assets
seems like somebody executed tests and commited them
commit 1780618543
Author: mauwii <Mauwii@outlook.de>
Date: Sun Nov 6 16:15:06 2022 +0100
update INSTALLING_MODELS.md
commit f91fd27624
Author: Kyle Schouviller <kyle0654@hotmail.com>
Date: Sat Nov 5 14:47:53 2022 -0700
Bug fix for inpaint size
commit 09e41e8f76
Author: Kyle Schouviller <kyle0654@hotmail.com>
Date: Sat Nov 5 14:34:52 2022 -0700
Add inpaint size options to inpaint at a larger size than the actual inpaint image, then scale back down for recombination
commit 6eeb2107b3
Author: mauwii <Mauwii@outlook.de>
Date: Sat Nov 5 21:01:14 2022 +0100
remove create-caches.yml since not used anywhere
commit 17053ad8b7
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 5 16:01:55 2022 -0400
fix duplicated argument introduced by conflict resolution
commit fefb4dc1f8
Merge: 762ca60ad05b1b35
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 5 12:47:35 2022 -0700
Merge branch 'development' into fix_generate.py
commit d05b1b3544
Author: Craig <cwallen@users.noreply.github.com>
Date: Sat Oct 29 20:40:30 2022 -0400
Resize hires as an image
commit 82d4904c07
Author: Craig <cwallen@users.noreply.github.com>
Date: Sat Oct 29 20:37:40 2022 -0400
Log strength with hires
commit 1cdcf33cfa
Merge: 6616fa83cbc029c6
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Nov 5 09:57:38 2022 -0400
Merge branch 'main' into development
- this synchronizes recent document fixes by mauwii
commit 6616fa835a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 4 00:47:03 2022 -0400
fix Windows library dependency issues
This commit addresses two bugs:
1) invokeai.py crashes immediately with a message about an undefined
attritube sigKILL (closes#1288). The fix is to pin torch at 1.12.1.
2) Version 1.4.2 of basicsr fails to load properly on Windows, and is
a requirement of realesrgan, however 1.4.1 works. Pinning basicsr
in our requirements file resulted in a dependency conflict, so I
ended up cloning realesrgan into the invoke-ai Git space and changing
the requirements file there.
If there is a more elegant solution, please advise.
commit 7b9a4564b1
Author: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Date: Sat Nov 5 14:36:45 2022 +0100
Update-docs (#1382)
* update IMG2IMG.md
* update INPAINTING.md
* update WEBUIHOTKEYS.md
* more doc updates (mostly fix formatting):
- OUTPAINTING.md
- POSTPROCESS.md
- PROMPTS.md
- VARIATIONS.md
- WEB.md
- WEBUIHOTKEYS.md
commit fcdefa0620
Author: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Date: Fri Nov 4 20:47:31 2022 +0100
Hotifx docs (#1376) (#1377)
commit ef8b3ce639
Merge: b704209536870a8f
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Nov 4 12:08:44 2022 -0400
Merge-main-into-development (#1373)
To get the rid of the difference between main and development.
Since otherwise it will be a pain to start fixing the documentatino
(when the state between main and development is not the same ...)
Also this should fix the problem of all tests failing since environment
yamls get updated.
commit 36870a8f53
Merge: 6b89adfab7042095
Author: Matthias Wild <40327258+mauwii@users.noreply.github.com>
Date: Fri Nov 4 16:25:00 2022 +0100
Merge branch 'development' into merge-main-into-development
commit b70420951d
Author: damian0815 <null@damianstewart.com>
Date: Thu Nov 3 12:39:45 2022 +0100
fix parsing error doing eg `forest ().swap(in winter)`
commit 1f0c5b4cf1
Author: wfng92 <43742196+wfng92@users.noreply.github.com>
Date: Thu Nov 3 17:13:52 2022 +0800
Use array slicing to calc ddim timesteps
commit 8648da8111
Author: mauwii <Mauwii@outlook.de>
Date: Fri Nov 4 00:06:19 2022 +0100
update environment-linux-aarch64 to use python 3.9
commit 45b4593563
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 3 22:31:46 2022 +0100
update environment-linux-aarch64.yml
- move getpass_asterisk to pip
commit 41b04316cf
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 3 20:40:08 2022 +0100
rename job, remove debug branch from triggers
commit e97c6db2a3
Author: mauwii <Mauwii@outlook.de>
Date: Thu Nov 3 20:34:01 2022 +0100
include build matrix to build x86_64 and aarch64
commit 896820a349
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 05:01:15 2022 +0100
disable caching
commit 06c8f468bf
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 04:26:39 2022 +0100
disable PR-Validation
since there are no files passed from context this is unecesarry
commit 61920e2701
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 04:09:39 2022 +0100
update action to use current branch
also update build-args of dockerfile and build.sh
commit f34ba7ca70
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 02:30:24 2022 +0100
remove unecesarry mkdir command again
commit c30ef0895d
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 01:51:12 2022 +0100
remove symlink to GFPGANv1.4
also re-add mkdir to prevent action from failing
commit aa3a774f73
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 01:48:59 2022 +0100
update build-container.yml to use cachev3
commit 2c30555b84
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 01:34:20 2022 +0100
update Dockerfile
- create models.yaml from models.yaml.example
- run preload_models.py with --no-interactive
commit 743f605773
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 01:21:15 2022 +0100
update build.sh to download sd-v1.5 model
commit 519c661abb
Author: mauwii <Mauwii@outlook.de>
Date: Tue Oct 25 01:26:50 2022 +0200
replace old fashined markdown templates with forms
this will help the readability of issues a lot 🤓
commit 22c956c75f
Merge: 13696adc0196571a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 3 10:20:21 2022 -0400
Merge branch 'development' of github.com:invoke-ai/InvokeAI into development
commit 13696adc3a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Nov 3 10:20:10 2022 -0400
speculative change to solve windows esrgan issues
commit 0196571a12
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 2 22:39:35 2022 -0400
remove merge markers from preload_models.py
commit 9666f466ab
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 2 18:29:34 2022 -0400
use refined model by default
commit 240e5486c8
Merge: 8164b6b9aa247e68
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 2 18:35:00 2022 -0400
Merge branch 'spezialspezial-patch-9' into development
commit 8164b6b9cf
Merge: 4fc82d55dd5a88dc
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Nov 2 17:06:46 2022 -0400
Merge branch 'development' of github.com:invoke-ai/InvokeAI into development
commit 4fc82d554f
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Thu Nov 3 04:17:28 2022 +1300
[WebUI] Final 2.1 Release Build
commit 96b34c0f85
Author: damian0815 <null@damianstewart.com>
Date: Wed Nov 2 09:08:11 2022 +0100
Final WebUI build for Release 2.1
- squashed commit of 52 commits from PR #1327
don't log base64 progress images
Fresh Build For WebUI
[WebUI] Loopback Default False
Fixes bugs/styling
- Fixes missing web app state on new version:
Adds stateReconciler to redux-persist.
When we add more values to the state and then release the update app, they will be automatically merged in.
Reseting web UI will be needed far less.
7159ec
- Fixes console z-index
- Moves reset web UI button to visible area
Decreases gallery width on inpainting
Increases workarea split padding to 1rem
Adds missing tooltips to site header
Changes inpainting controls settings to hover
Fixes hotkeys and settings buttons not working
Improves bounding box interactions
- Bounding box can now be moved by dragging any of its edges
- Bounding box does not affect drawing if already drawing a stroke
- Can lock bounding box to draw directly on the bounding box edges
- Removes spacebar-hold behaviour due to technical issues
Fixes silent crash when init image too large
To send the mask to the server, the UI rendered the mask onto the init image and sent the whole image. The mask was then cropped by the server.
If the image was too large, the app silently failed. Maybe it exceeds the websocket size limit.
Fixed by cropping the mask in the UI layer, sending only bounding-box-sized mask image data.
Disabled bounding box settings when locked
Styles image uploader
Builds fresh bundle
Improves bounding box interaction
Added spacebar-hold-to-transform back.
Address bounding box feedback
- Adds back toggle to hide bounding box
- Box quick toggle = q, normal toggle = shift + q
- Styles canvas alert icons
Adds hints when unable to invoke
- Popover on Invoke button indicates why exactly it is disabled, e.g. prompt is empty, something else is processing, etc.
- There may be more than one reason; all are displayed.
Fix Inpainting Alerts Styling
Preventing unnecessary re-renders across the app
Code Split Inpaint Options
Isolate features to their own components so they dont re-render the other stuff each time.
[TESTING] Remove global isReady checking
I dont believe this is need at all because the isready state is constantly updated when needed and tracked real time in the Redux store. This causes massive re-renders. @psychedelicious If this is absolutely essential for a reason that I do not see, please hit me up on Discord.
Fresh Bundle
Fix Bounding Box Settings re-rendering on brush stroke
[Code Splitting] Bounding Box Options
Isolated all bounding box components to trigger unnecessary re-renders. Still need to fix bounding box triggering re-renders on the control panel inside the canvas itself. But the options panel should be a good to go with this change.
Inpainting Controls Code Spitting and Performance
Codesplit the entirety of the inpainting controls. Created new selectors for each and every component to ensure there are no unnecessary re-renders. App feels a lot smoother.
Fixes rerenders on ClearBrushHistory
Fixes crash when requesting post-generation upscale/face restoration
- Moves the inpainting paste to before the postprocessing.
Removes unused isReady state
Changes Report Bug icon to a bug
Restores shift+q bounding box shortcut
Adds alert for bounding box size to status icons
Adds asCheckbox to IAIIconButton
Rough draft of this. Not happy with the styling but it's clearer than having them look just like buttons.
Fixes crash related to old value of progress_latents in state
Styling changes and settings modal minor refactor
Fixes: uploaded JPG images not loading
Reworks CurrentImageButtons.tsx
- Change all icons to FA iconset for consistency
- Refactors IAIIconButton, IAIButton, IAIPopover to handle ref forwarding
- Redesigns buttons into group
Only generate 1 iteration when seed fixed & variations disabled
Fixes progress images select
Fixes edge case: upload over gets stuck while alt tabbing
- Press esc to close it now
Fixes display progress images select typing
Fixes current image button rerenders
Adds min width to ImageUploader
Makes fast-latents in progress default
Update Icon Button Checkbox Style Styling
Fixes next/prev image buttons
Refactor canvas buttons + more
Add Save Intermediates Step Count
For accurate mode only.
Co-Authored-By: Richard Macarthy <richardmacarthy@protonmail.com>
Restores "initial image" text
Address feedback
- moves mask clear button
- fixes intermediates
- shrinks inpainting icons by 10%
Fix Loopback Styling
Adds escape hotkey to close floating panels
Readd Hotkey for Dual Display
Updated Current Image Button Styling
commit dd5a88dcee
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Thu Nov 3 04:17:28 2022 +1300
[WebUI] Final 2.1 Release Build
commit 95ed56bf82
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Thu Nov 3 04:16:31 2022 +1300
Updated Current Image Button Styling
commit 1ae80f5ab9
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Thu Nov 3 04:07:57 2022 +1300
Readd Hotkey for Dual Display
commit 1f0bd3ca6c
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Thu Nov 3 02:07:00 2022 +1100
Adds escape hotkey to close floating panels
commit a1971f6830
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Thu Nov 3 03:38:15 2022 +1300
Fix Loopback Styling
commit c6118e8898
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Thu Nov 3 01:29:51 2022 +1100
Address feedback
- moves mask clear button
- fixes intermediates
- shrinks inpainting icons by 10%
commit 7ba958cf7f
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Thu Nov 3 01:10:38 2022 +1100
Restores "initial image" text
commit 383905d5d2
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Thu Nov 3 02:59:11 2022 +1300
Add Save Intermediates Step Count
For accurate mode only.
Co-Authored-By: Richard Macarthy <richardmacarthy@protonmail.com>
commit 6173e3e9ca
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Thu Nov 3 00:53:53 2022 +1100
Refactor canvas buttons + more
commit 3feb7d8922
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Thu Nov 3 00:49:23 2022 +1100
Fixes next/prev image buttons
commit 1d9edbd0dd
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Thu Nov 3 00:50:44 2022 +1300
Update Icon Button Checkbox Style Styling
commit d439abdb89
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 21:37:24 2022 +1100
Makes fast-latents in progress default
commit ee47ea0c89
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 21:37:09 2022 +1100
Adds min width to ImageUploader
commit 300bb2e627
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 21:28:22 2022 +1100
Fixes current image button rerenders
commit ccf8593501
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 21:27:43 2022 +1100
Fixes display progress images select typing
commit 0fda612f3f
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 21:02:01 2022 +1100
Fixes edge case: upload over gets stuck while alt tabbing
- Press esc to close it now
commit 5afff65b71
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 20:33:19 2022 +1100
Fixes progress images select
commit 7e55bdefce
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 20:27:47 2022 +1100
Only generate 1 iteration when seed fixed & variations disabled
commit 620cf84d3d
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 19:51:38 2022 +1100
Reworks CurrentImageButtons.tsx
- Change all icons to FA iconset for consistency
- Refactors IAIIconButton, IAIButton, IAIPopover to handle ref forwarding
- Redesigns buttons into group
commit cfe567c62a
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 16:14:50 2022 +1100
Fixes: uploaded JPG images not loading
commit cefe12f1df
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 15:31:18 2022 +1100
Styling changes and settings modal minor refactor
commit 1e51c39928
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 15:27:46 2022 +1100
Fixes crash related to old value of progress_latents in state
commit 42a02bbb80
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 13:15:06 2022 +1100
Adds asCheckbox to IAIIconButton
Rough draft of this. Not happy with the styling but it's clearer than having them look just like buttons.
commit f1ae6dae4c
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 13:13:56 2022 +1100
Adds alert for bounding box size to status icons
commit 6195579910
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 11:52:19 2022 +1100
Restores shift+q bounding box shortcut
commit 16c8b23b34
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 11:32:07 2022 +1100
Changes Report Bug icon to a bug
commit 07ae626b22
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 11:17:16 2022 +1100
Removes unused isReady state
commit 8d171bb044
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 11:13:26 2022 +1100
Fixes crash when requesting post-generation upscale/face restoration
- Moves the inpainting paste to before the postprocessing.
commit 6e33ca7e9e
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Wed Nov 2 10:59:01 2022 +1100
Fixes rerenders on ClearBrushHistory
commit db46e12f2b
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 11:36:28 2022 +1300
Inpainting Controls Code Spitting and Performance
Codesplit the entirety of the inpainting controls. Created new selectors for each and every component to ensure there are no unnecessary re-renders. App feels a lot smoother.
commit 868e4b2db8
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 07:40:31 2022 +1300
[Code Splitting] Bounding Box Options
Isolated all bounding box components to trigger unnecessary re-renders. Still need to fix bounding box triggering re-renders on the control panel inside the canvas itself. But the options panel should be a good to go with this change.
commit 2e562742c1
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 06:40:27 2022 +1300
Fix Bounding Box Settings re-rendering on brush stroke
commit 68e6958009
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 06:28:34 2022 +1300
Fresh Bundle
commit ea6e3a7949
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 06:26:56 2022 +1300
[TESTING] Remove global isReady checking
I dont believe this is need at all because the isready state is constantly updated when needed and tracked real time in the Redux store. This causes massive re-renders. @psychedelicious If this is absolutely essential for a reason that I do not see, please hit me up on Discord.
commit b2879ca99f
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 06:08:59 2022 +1300
Code Split Inpaint Options
Isolate features to their own components so they dont re-render the other stuff each time.
commit 4e911566c3
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 03:50:56 2022 +1300
Preventing unnecessary re-renders across the app
commit 9bafda6a15
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 03:02:35 2022 +1300
Fix Inpainting Alerts Styling
commit 871a8a5375
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 23:52:07 2022 +1100
Adds hints when unable to invoke
- Popover on Invoke button indicates why exactly it is disabled, e.g. prompt is empty, something else is processing, etc.
- There may be more than one reason; all are displayed.
commit 0eef74bc00
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 23:40:11 2022 +1100
Address bounding box feedback
- Adds back toggle to hide bounding box
- Box quick toggle = q, normal toggle = shift + q
- Styles canvas alert icons
commit 423ae32097
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 17:06:07 2022 +1100
Improves bounding box interaction
Added spacebar-hold-to-transform back.
commit 8282e5d045
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 16:57:07 2022 +1100
Builds fresh bundle
commit 19305cdbdf
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 16:51:11 2022 +1100
Styles image uploader
commit eb9028ab30
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 16:51:03 2022 +1100
Disabled bounding box settings when locked
commit 21483f5d07
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 16:50:24 2022 +1100
Fixes silent crash when init image too large
To send the mask to the server, the UI rendered the mask onto the init image and sent the whole image. The mask was then cropped by the server.
If the image was too large, the app silently failed. Maybe it exceeds the websocket size limit.
Fixed by cropping the mask in the UI layer, sending only bounding-box-sized mask image data.
commit 82dcbac28f
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 16:28:30 2022 +1100
Improves bounding box interactions
- Bounding box can now be moved by dragging any of its edges
- Bounding box does not affect drawing if already drawing a stroke
- Can lock bounding box to draw directly on the bounding box edges
- Removes spacebar-hold behaviour due to technical issues
commit d43bd4625d
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 15:10:49 2022 +1100
Fixes hotkeys and settings buttons not working
commit ea891324a2
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 11:04:02 2022 +1100
Changes inpainting controls settings to hover
commit 8fd9ea2193
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 11:03:41 2022 +1100
Adds missing tooltips to site header
commit fb02666856
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 11:03:25 2022 +1100
Increases workarea split padding to 1rem
commit f6f5c2731b
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 11:03:10 2022 +1100
Decreases gallery width on inpainting
commit b4e3f771e0
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 10:54:59 2022 +1100
Fixes bugs/styling
- Fixes missing web app state on new version:
Adds stateReconciler to redux-persist.
When we add more values to the state and then release the update app, they will be automatically merged in.
Reseting web UI will be needed far less.
7159ec
- Fixes console z-index
- Moves reset web UI button to visible area
commit 99bb9491ac
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Tue Nov 1 08:35:45 2022 +1300
[WebUI] Loopback Default False
commit 0453f21127
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Wed Nov 2 23:23:51 2022 +1300
Fresh Build For WebUI
commit 9fc09aa4bd
Author: damian0815 <null@damianstewart.com>
Date: Wed Nov 2 09:08:11 2022 +0100
don't log base64 progress images
commit 5e87062cf8
Author: spezialspezial <75758219+spezialspezial@users.noreply.github.com>
Date: Wed Nov 2 00:21:27 2022 +0100
Option to directly invert the grayscale heatmap - fix
commit 3e7a459990
Author: spezialspezial <75758219+spezialspezial@users.noreply.github.com>
Date: Tue Nov 1 21:37:33 2022 +0100
Update txt2mask.py
commit bbf4c03e50
Author: spezialspezial <75758219+spezialspezial@users.noreply.github.com>
Date: Tue Nov 1 21:11:19 2022 +0100
Option to directly invert the grayscale heatmap
Theoretically less work inverting the image while it's small but I can't measure a significant difference. Though, handy option to have in some cases.
commit 611a3a9753
Author: mauwii <Mauwii@outlook.de>
Date: Wed Nov 2 02:23:09 2022 +0100
fix name of caching step
commit 1611f0d181
Author: mauwii <Mauwii@outlook.de>
Date: Wed Nov 2 02:18:46 2022 +0100
readd caching of sd-models
- this would remove the necesarrity of the secret availability in PRs
commit 08835115e4
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 1 22:10:12 2022 -0400
pin pytorch_lightning to 1.7.7, issue #1331
commit 2d84e28d32
Merge: 533fd04eef17aae8
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 1 22:11:04 2022 -0400
Merge branch 'development' of github.com:invoke-ai/InvokeAI into development
commit ef17aae8ab
Author: damian0815 <null@damianstewart.com>
Date: Wed Nov 2 00:39:48 2022 +0100
add damian0815 to contributors list
commit 0cc39f01a3
Author: damian0815 <null@damianstewart.com>
Date: Wed Nov 2 01:18:50 2022 +0100
report full size for fast latents and update conversion matrix for v1.5
commit 688d7258f1
Author: damian0815 <null@damianstewart.com>
Date: Wed Nov 2 00:33:00 2022 +0100
fix a bug that broke cross attention control index mapping
commit 4513320bf1
Author: damian0815 <null@damianstewart.com>
Date: Wed Nov 2 00:31:58 2022 +0100
save VRAM by not recombining tensors that have been sliced to save VRAM
commit 533fd04ef0
Merge: 6215592bdff5681c
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 1 17:40:36 2022 -0400
Merge branch 'development' of github.com:invoke-ai/InvokeAI into development
commit dff5681cf0
Author: damian0815 <d@d.com>
Date: Tue Nov 1 13:56:03 2022 +0100
shorter strings
commit 5a2790a69b
Author: damian0815 <d@d.com>
Date: Tue Nov 1 13:19:20 2022 +0100
convert progress display to a drop-down
commit 7c5305ccba
Author: damian0815 <d@d.com>
Date: Tue Nov 1 12:54:46 2022 +0100
do not try to save base64 intermediates in gallery on cancellation
commit 4013e8ad6f
Author: psychedelicious <4822129+psychedelicious@users.noreply.github.com>
Date: Tue Nov 1 21:54:35 2022 +1100
Fixes b64 image sending and displaying
commit d1dfd257f9
Author: damian <d@d.com>
Date: Tue Nov 1 11:40:40 2022 +0100
wip base64
commit 5322d735ee
Author: damian <d@d.com>
Date: Tue Nov 1 11:31:42 2022 +0100
update frontend
commit cdb107dcda
Author: damian <d@d.com>
Date: Tue Nov 1 11:17:43 2022 +0100
add option to show intermediate latent space
commit be1393a41c
Author: damian <d@d.com>
Date: Tue Nov 1 10:16:55 2022 +0100
ensure existing exception handling code also handles new exception class
commit e554c2607f
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Nov 1 10:08:42 2022 +0100
Rebuilt prompt parsing logic
Complete re-write of the prompt parsing logic to be more readable and
logical, and therefore also hopefully easier to debug, maintain, and
augment.
In the process it has also become more robust to badly-formed prompts.
Squashed commit of the following:
commit 8fcfa88a16e1390d41717e940d72aed64712171c
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 30 17:05:57 2022 +0100
further cleanup
commit 1a1fd78bcfeb49d072e3e6d5808aa8df15441629
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 30 16:07:57 2022 +0100
cleanup and document
commit 099c9659fa8b8135876f9a5a50fe80b20bc0635c
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 30 15:54:58 2022 +0100
works fully
commit 5e6887ea8c25a1e21438ff6defb381fd027d25fd
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 30 15:24:31 2022 +0100
further...
commit 492fda120844d9bc1ad4ec7dd408a3374762d0ff
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 30 14:08:57 2022 +0100
getting there...
commit c6aab05a8450cc3c95c8691daf38fdc64c74f52d
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 28 14:29:03 2022 +0200
wip doesn't compile
commit 5e533f731cfd20cd435330eeb0012e5689e87e81
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 28 13:21:43 2022 +0200
working with CrossAttentionCtonrol but no Attention support yet
commit 9678348773431e500e110e8aede99086bb7b5955
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 28 13:04:52 2022 +0200
wip rebuiling prompt parser
commit 6215592b12
Merge: ef24d76a349cc254
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 1 17:34:55 2022 -0400
Merge branch 'development' of github.com:invoke-ai/InvokeAI into development
commit 349cc25433
Author: damian0815 <d@d.com>
Date: Tue Nov 1 20:08:52 2022 +0100
fix crash (be a little less aggressive clearing out the attention slice)
commit 214d276379
Author: damian0815 <d@d.com>
Date: Tue Nov 1 19:57:55 2022 +0100
be more aggressive at clearing out saved_attn_slice
commit ef24d76adc
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 1 14:34:23 2022 -0400
fix library problems in preload_modules
commit ab2b5a691d
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Nov 1 17:22:48 2022 -0400
fix model_cache memory management issues
commit c7de2b2801
Author: mauwii <Mauwii@outlook.de>
Date: Tue Nov 1 02:02:14 2022 +0100
disable checks with sd-V1.4 model...
...to save some resources, since V1.5 is the default now
commit e8075658ac
Author: mauwii <Mauwii@outlook.de>
Date: Mon Oct 31 22:20:51 2022 +0100
update test-invoke-conda.yml
- fix model dl path for sd-v1-4.ckpt
- copy configs/models.yaml.example to configs/models.yaml
commit 4202dabee1
Author: mauwii <Mauwii@outlook.de>
Date: Mon Oct 31 22:17:21 2022 +0100
fix models example weights for sd-v1.4
commit d67db2bcf1
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Tue Nov 1 08:35:45 2022 +1300
[WebUI] Loopback Default False
commit 7159ec885f
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Oct 31 11:33:05 2022 -0400
further improvements to preload_models.py
- Faster startup for command line switch processing
- Specify configuration file to modify using --config option:
./scripts/preload_models.ply --config models/my-models-file.yaml
commit b5cf734ba9
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Oct 31 11:08:19 2022 -0400
improve behavior of preload_models.py
- NEVER overwrite user's existing models.yaml
- Instead, merge its contents into new config file,
and rename original to models.yaml.orig (with
message)
- models.yaml has been removed from repository and renamed
models.yaml.example
commit f7dc8eafee
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Oct 31 10:47:35 2022 -0400
restore models.yaml to virgin state
commit 762ca60a30
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Oct 4 22:55:10 2022 -0400
Update INPAINTING.md
commit e7fb9f342c
Author: Hideyuki Katsushiro <h.katsushiro@qualia.tokyo.jp>
Date: Wed Oct 5 10:08:53 2022 +0900
add argument --outdir
This commit addresses two bugs:
1) invokeai.py crashes immediately with a message about an undefined
attritube sigKILL (closes#1288). The fix is to pin torch at 1.12.1.
2) Version 1.4.2 of basicsr fails to load properly on Windows, and is
a requirement of realesrgan, however 1.4.1 works. Pinning basicsr
in our requirements file resulted in a dependency conflict, so I
ended up cloning realesrgan into the invoke-ai Git space and changing
the requirements file there.
If there is a more elegant solution, please advise.
- Due to misuse of rebase command, main was transiently
in an inconsistent state.
- This repairs the damage, and adds a few post-release
patches that ensure stable conda installs on Mac and Windows.
- squashed commit of 52 commits from PR #1327
don't log base64 progress images
Fresh Build For WebUI
[WebUI] Loopback Default False
Fixes bugs/styling
- Fixes missing web app state on new version:
Adds stateReconciler to redux-persist.
When we add more values to the state and then release the update app, they will be automatically merged in.
Reseting web UI will be needed far less.
7159ec
- Fixes console z-index
- Moves reset web UI button to visible area
Decreases gallery width on inpainting
Increases workarea split padding to 1rem
Adds missing tooltips to site header
Changes inpainting controls settings to hover
Fixes hotkeys and settings buttons not working
Improves bounding box interactions
- Bounding box can now be moved by dragging any of its edges
- Bounding box does not affect drawing if already drawing a stroke
- Can lock bounding box to draw directly on the bounding box edges
- Removes spacebar-hold behaviour due to technical issues
Fixes silent crash when init image too large
To send the mask to the server, the UI rendered the mask onto the init image and sent the whole image. The mask was then cropped by the server.
If the image was too large, the app silently failed. Maybe it exceeds the websocket size limit.
Fixed by cropping the mask in the UI layer, sending only bounding-box-sized mask image data.
Disabled bounding box settings when locked
Styles image uploader
Builds fresh bundle
Improves bounding box interaction
Added spacebar-hold-to-transform back.
Address bounding box feedback
- Adds back toggle to hide bounding box
- Box quick toggle = q, normal toggle = shift + q
- Styles canvas alert icons
Adds hints when unable to invoke
- Popover on Invoke button indicates why exactly it is disabled, e.g. prompt is empty, something else is processing, etc.
- There may be more than one reason; all are displayed.
Fix Inpainting Alerts Styling
Preventing unnecessary re-renders across the app
Code Split Inpaint Options
Isolate features to their own components so they dont re-render the other stuff each time.
[TESTING] Remove global isReady checking
I dont believe this is need at all because the isready state is constantly updated when needed and tracked real time in the Redux store. This causes massive re-renders. @psychedelicious If this is absolutely essential for a reason that I do not see, please hit me up on Discord.
Fresh Bundle
Fix Bounding Box Settings re-rendering on brush stroke
[Code Splitting] Bounding Box Options
Isolated all bounding box components to trigger unnecessary re-renders. Still need to fix bounding box triggering re-renders on the control panel inside the canvas itself. But the options panel should be a good to go with this change.
Inpainting Controls Code Spitting and Performance
Codesplit the entirety of the inpainting controls. Created new selectors for each and every component to ensure there are no unnecessary re-renders. App feels a lot smoother.
Fixes rerenders on ClearBrushHistory
Fixes crash when requesting post-generation upscale/face restoration
- Moves the inpainting paste to before the postprocessing.
Removes unused isReady state
Changes Report Bug icon to a bug
Restores shift+q bounding box shortcut
Adds alert for bounding box size to status icons
Adds asCheckbox to IAIIconButton
Rough draft of this. Not happy with the styling but it's clearer than having them look just like buttons.
Fixes crash related to old value of progress_latents in state
Styling changes and settings modal minor refactor
Fixes: uploaded JPG images not loading
Reworks CurrentImageButtons.tsx
- Change all icons to FA iconset for consistency
- Refactors IAIIconButton, IAIButton, IAIPopover to handle ref forwarding
- Redesigns buttons into group
Only generate 1 iteration when seed fixed & variations disabled
Fixes progress images select
Fixes edge case: upload over gets stuck while alt tabbing
- Press esc to close it now
Fixes display progress images select typing
Fixes current image button rerenders
Adds min width to ImageUploader
Makes fast-latents in progress default
Update Icon Button Checkbox Style Styling
Fixes next/prev image buttons
Refactor canvas buttons + more
Add Save Intermediates Step Count
For accurate mode only.
Co-Authored-By: Richard Macarthy <richardmacarthy@protonmail.com>
Restores "initial image" text
Address feedback
- moves mask clear button
- fixes intermediates
- shrinks inpainting icons by 10%
Fix Loopback Styling
Adds escape hotkey to close floating panels
Readd Hotkey for Dual Display
Updated Current Image Button Styling
1. added nvidia channel to environment.yml
2. updated pytorch-cuda requirement
3. let conda figure out what version of pytorch to install
4. add conda install status checking to .bat and .sh install files
5. in preload_models.py catch and handle download/access token errors
- Faster startup for command line switch processing
- Specify configuration file to modify using --config option:
./scripts/preload_models.ply --config models/my-models-file.yaml
- NEVER overwrite user's existing models.yaml
- Instead, merge its contents into new config file,
and rename original to models.yaml.orig (with
message)
- models.yaml has been removed from repository and renamed
models.yaml.example
The OutsideWatcher was disabling hotkeys because it was always being active -- whether the object was pinned or not. Modified the hook to now take a new optional argument called "req" which is a boolean that indicates whether to trigger it or not.
We can pass this from the component to control when the outside watcher should work and when it shouldn't.
- ldm.generate.Generator() now takes an argument named `max_load_models`.
This is an integer that limits the model cache size. When the cache
reaches the limit, it will start purging older models from cache.
- CLI takes an argument --max_load_models, default to 2. This will keep
one model in GPU and the other in CPU and switch back and forth
quickly.
- To not cache models at all, pass --max_load_models=1
- ldm.generate.Generator() now takes an argument named `max_load_models`.
This is an integer that limits the model cache size. When the cache
reaches the limit, it will start purging older models from cache.
- CLI takes an argument --max_load_models, default to 2. This will keep
one model in GPU and the other in CPU and switch back and forth
quickly.
- To not cache models at all, pass --max_load_models=1
- User can choose to download just recommended models, customize list to download,
or skip downloading altogether.
- Does direct download to models directory instead of to HuggingFace cache
- Able to resume interrupted downloads
- pull_request_target trigger does not verify the requesters commit(s)
- is more to be used for automations like labeling, commenting, ...
- stuff where a token with write access to the repo is necesarry
- user can select which weight files to download using huggingface cache
- user must log in to huggingface, generate an access token, and accept
license terms the very first time this is run. After that, everything
works automatically.
- added placeholder for docs for installing models
- also got rid of unused config files. hopefully they weren't needed
for textual inversion, but I don't think so.
- in this way the action is used from the base repository
- also use new secret HUGGINGFACE_TOKEN (username:token)
- f.e. `noreply@github.com:hf_lkaugfklagwrjglaslzfgkjzzf`
- change pr prompt file to validate_pr_prompt.txt
The Args object would crap out when trying to retrieve metadata from
an image file that did not contain InvokeAI-generated metadata, such
as a JPG. This corrects that and returns dummy values (seed of zero,
prompt of '') to avoid downstream breakage.
The k_samplers come with a "karras" noise schedule which performs
very well at low step counts but becomes noisy at higher ones.
This commit introduces a threshold (currently 30 steps) at which the
k samplers will switch over from using karras to the older model
noise schedule.
- This sets a step switchover point at which the k-samplers stop using the
Karras noise schedule and start using the LatentDiffusion noise schedule.
The advantage of this is that the Karras schedule produces excellent
results at low step counts but starts to become unstable at high
steps.
- A new command argument --karras_max, lets the user set where the
switchover occurs. Default is 29 steps (1-29 steps Karras),
(30 or greater LDM)
- Tildebyte, sorry to do a fast forward three-way merge for this
but rebasing was just too painful due to extensive recent
changes to the diffuser code.
This was a difficult merge because both PR #1108 and #1243 made
changes to obscure parts of the diffusion code.
- prompt weighting, merging and cross-attention working
- cross-attention does not work with runwayML inpainting
model, but weighting and merging are tested and working
- CLI command parsing code rewritten in order to get embedded
quotes right
- --hires now works with runwayML inpainting
- --embiggen does not work with runwayML and will give an error
- Added an --invert option to invert masks applied to inpainting
- Updated documentation
- change default model back to 1.4
- remove --fnformat from canonicalized dream prompt arguments
(not needed for image reproducibility)
- add -tm to canonicalized dream prompt arguments
(definitely needed for image reproducibility)
- The plms sampler now works with custom inpainting model
- Quashed bug that was causing generation on normal models to fail (oops!)
- Can now generate non-square images with custom inpainting model
Credits for advice and assistance during porting:
@any-winter-4079 (http://github.com/any-winter-4079)
@db3000 (Danny Beer http://github.com/db3000)
- The plms sampler now works with custom inpainting model
- Quashed bug that was causing generation on normal models to fail (oops!)
- Can now generate non-square images with custom inpainting model
This is still a work in progress but seems functional. It supports
inpainting, txt2img and img2img on the ddim and k* samplers (plms
still needs work, but I know what to do).
To test this, get the file `sd-v1-5-inpainting.ckpt' from
https://huggingface.co/runwayml/stable-diffusion-inpainting and place it
at `models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt`
Launch invoke.py with --model inpainting-1.5 and proceed as usual.
Caveats:
1. The inpainting model takes about 800 Mb more memory than the standard
1.5 model. This model will not work on 4 GB cards.
2. The inpainting model is temperamental. It wants you to describe the
entire scene and not just the masked area to replace. So if you want
to replace the parrot on a man's shoulder with a crow, the prompt
"crow" may fail. Try "man with a crow on shoulder" instead. The
symptom of a failed inpainting is that the area will be erased and
replaced with background.
3. This has not been tested well. Please report bugs.
- This is a merge of the final version of PR #1218 "Inpainting
Improvements"
Various merge conflicts made it easier to commit directly.
Author: Kyle0654
Co-Author: lstein
- This is a merge of the final version of PR #1218 "Inpainting
Improvements"
Various merge conflicts made it easier to commit directly.
Author: Kyle0654
Co-Author: lstein
Now you can activate the Hugging Face `diffusers` library safety check
for NSFW and other potentially disturbing imagery.
To turn on the safety check, pass --safety_checker at the command
line. For developers, the flag is `safety_checker=True` passed to
ldm.generate.Generate(). Once the safety checker is turned on, it
cannot be turned off unless you reinitialize a new Generate object.
When the safety checker is active, suspect images will be blurred and
a warning icon is added. There is also a warning message printed in
the CLI, but it can be a little hard to see because of its positioning
in the output stream.
There is a slight but noticeable delay when the safety checker runs.
Note that invisible watermarking is *not* currently implemented. The
watermark code distributed by the CompViz distribution uses a library
that does not seem to be able to retrieve the watermarks it creates,
and it does not appear that Hugging Face `diffusers` or other SD
distributions are doing any watermarking.
1. If tensors are passed to inpaint as init_image and/or init_mask, then
the post-generation image fixup code will be skipped.
2. Post-generation image fixup will work with either a black and white "L"
or "RGB" mask, or an "RGBA" mask.
- pass a PIL.Image to img2img and inpaint rather than tensor
- To support clipseg, inpaint needs to accept an "L" or "1" format
mask. Made the appropriate change.
To add a VAE autoencoder to an existing model:
1. Download the appropriate autoencoder and put it into
models/ldm/stable-diffusion
Note that you MUST use a VAE that was written for the
original CompViz Stable Diffusion codebase. For v1.4,
that would be the file named vae-ft-mse-840000-ema-pruned.ckpt
that you can download from https://huggingface.co/stabilityai/sd-vae-ft-mse-original
2. Edit config/models.yaml to contain the following stanza, modifying `weights`
and `vae` as required to match the weights and vae model file names. There is
no requirement to rename the VAE file.
~~~
stable-diffusion-1.4:
weights: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
description: Stable Diffusion v1.4
config: configs/stable-diffusion/v1-inference.yaml
vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
width: 512
height: 512
~~~
3. Alternatively from within the `invoke.py` CLI, you may use the command
`!editmodel stable-diffusion-1.4` to bring up a simple editor that will
allow you to add the path to the VAE.
4. If you are just installing InvokeAI for the first time, you can also
use `!import_model models/ldm/stable-diffusion/sd-v1.4.ckpt` instead
to create the configuration from scratch.
5. That's it!
* Removed duplicate fix_func for MPS
* add support for loading VAE autoencoders
To add a VAE autoencoder to an existing model:
1. Download the appropriate autoencoder and put it into
models/ldm/stable-diffusion
Note that you MUST use a VAE that was written for the
original CompViz Stable Diffusion codebase. For v1.4,
that would be the file named vae-ft-mse-840000-ema-pruned.ckpt
that you can download from https://huggingface.co/stabilityai/sd-vae-ft-mse-original
2. Edit config/models.yaml to contain the following stanza, modifying `weights`
and `vae` as required to match the weights and vae model file names. There is
no requirement to rename the VAE file.
~~~
stable-diffusion-1.4:
weights: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
description: Stable Diffusion v1.4
config: configs/stable-diffusion/v1-inference.yaml
vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
width: 512
height: 512
~~~
3. Alternatively from within the `invoke.py` CLI, you may use the command
`!editmodel stable-diffusion-1.4` to bring up a simple editor that will
allow you to add the path to the VAE.
4. If you are just installing InvokeAI for the first time, you can also
use `!import_model models/ldm/stable-diffusion/sd-v1.4.ckpt` instead
to create the configuration from scratch.
5. That's it!
* ported code refactor changes from PR #1221
- pass a PIL.Image to img2img and inpaint rather than tensor
- To support clipseg, inpaint needs to accept an "L" or "1" format
mask. Made the appropriate change.
* minor fixes to inpaint code
1. If tensors are passed to inpaint as init_image and/or init_mask, then
the post-generation image fixup code will be skipped.
2. Post-generation image fixup will work with either a black and white "L"
or "RGB" mask, or an "RGBA" mask.
Co-authored-by: wfng92 <43742196+wfng92@users.noreply.github.com>
The k_samplers come with a "karras" noise schedule which performs
very well at low step counts but becomes noisy at higher ones.
This commit introduces a threshold (currently 30 steps) at which the
k samplers will switch over from using karras to the older model
noise schedule.
1. If tensors are passed to inpaint as init_image and/or init_mask, then
the post-generation image fixup code will be skipped.
2. Post-generation image fixup will work with either a black and white "L"
or "RGB" mask, or an "RGBA" mask.
- pass a PIL.Image to img2img and inpaint rather than tensor
- To support clipseg, inpaint needs to accept an "L" or "1" format
mask. Made the appropriate change.
To add a VAE autoencoder to an existing model:
1. Download the appropriate autoencoder and put it into
models/ldm/stable-diffusion
Note that you MUST use a VAE that was written for the
original CompViz Stable Diffusion codebase. For v1.4,
that would be the file named vae-ft-mse-840000-ema-pruned.ckpt
that you can download from https://huggingface.co/stabilityai/sd-vae-ft-mse-original
2. Edit config/models.yaml to contain the following stanza, modifying `weights`
and `vae` as required to match the weights and vae model file names. There is
no requirement to rename the VAE file.
~~~
stable-diffusion-1.4:
weights: models/ldm/stable-diffusion-v1/sd-v1-4.ckpt
description: Stable Diffusion v1.4
config: configs/stable-diffusion/v1-inference.yaml
vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
width: 512
height: 512
~~~
3. Alternatively from within the `invoke.py` CLI, you may use the command
`!editmodel stable-diffusion-1.4` to bring up a simple editor that will
allow you to add the path to the VAE.
4. If you are just installing InvokeAI for the first time, you can also
use `!import_model models/ldm/stable-diffusion/sd-v1.4.ckpt` instead
to create the configuration from scratch.
5. That's it!
Ironically, the black and white mask file generated by the
`invoke> !mask` command could not be passed as the mask to
`img2img`. This is now fixed and the documentation updated.
- remove unsupported testtubelogger, use csvlogger instead
- fix logic for parsing --gpus option so that it won't crash if
trailing comma absent
- change trainer accelerator from unsupported 'ddp' to 'auto'
- code for committing config changes to models.yaml now in module
rather than in invoke script
- model marked "default" is now loaded if model not specified on
command line
- uncache changed models when edited, so that they reload properly
- removed liaon from models.yaml and added stable-diffusion-1.5
- The !mask command takes an image path, a text prompt, and
(optionally) a masking threshold. It creates a mask over the region
indicated by the prompt, and outputs several files that show which
regions will be masked by the chosen prompt and threshold.
- The mask images should not be passed directly to img2img because
they are designed for visualization only. Instead, use the
--text_mask option to pass the selected prompt and threshold.
- See docs/features/INPAINTING.md for details.
- The directory "models" in the main InvokeAI directory was conflicting
with loading "models.clipseg". To fix this issue, I have renamed the
models.clipseg to clipseg_models.clipseg, and applied this change to
the 'models-rename' branch of invoke-ai's fork of clipseg.
attention is parsed but ignored, blends old syntax doesn't work,
conjunctions are parsed but ignored, the only part that's used
here is the new .blend() syntax and cross-attention control
using .swap()
commit 9bb0b5d0036c4dffbb72ce11e097fae4ab63defd
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sat Oct 15 23:43:41 2022 +0200
undo local_files_only stuff
commit eed93f5d30c34cfccaf7497618ae9af17a5ecfbb
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sat Oct 15 23:40:37 2022 +0200
Revert "Merge branch 'development-invoke' into fix-prompts"
This reverts commit 7c40892a9f184f7e216f14d14feb0411c5a90e24, reversing
changes made to e3f2dd62b0548ca6988818ef058093a4f5b022f2.
commit f06d6024e345c69e6d5a91ab5423925a68ee95a7
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Thu Oct 13 23:30:16 2022 +0200
more efficiently handle multiple conditioning
commit 5efdfcbcd980ce6202ab74e7f90e7415ce7260da
Merge: b9c0dc5 ac08bb6
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Thu Oct 13 14:51:01 2022 +0200
Merge branch 'optional-disable-karras-schedule' into fix-prompts
commit ac08bb6fd25e19a9d35cf6c199e66500fb604af1
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Thu Oct 13 14:50:43 2022 +0200
append '*use_model_sigmas*' to prompt string to use model sigmas
commit 70d8c05a3ff329409f76204f4af94e55d468ab8b
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Thu Oct 13 12:12:17 2022 +0200
make karras scheduling switchable
commit d60df54f69 replaced the model's
own scheduling with karras scheduling. this has changed image generation
(seems worse now?)
this commit wraps the change in a bool.
commit b9c0dc5f1a658a0e6c3936000e9ae559e1c7a1db
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 20:16:00 2022 +0200
add test of more complex conjunction
commit 9ac0c15cc0d7b5f6df3289d3ad474260972a17be
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 17:18:25 2022 +0200
improve comments
commit ad33bce60590b87b2a93e90f16dc9d3e935d04a5
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 17:04:46 2022 +0200
put back thresholding stuff
commit 4852c698a325049834ba0d4b358f07210bc7171a
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 14:25:02 2022 +0200
notes on improving conjunction efficiency
commit a53bb1e5b68025d09642b935ae6a9a015cfaf2d6
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 14:14:33 2022 +0200
optional weights support for Conjunction
commit fec79ab15e4f0c84dd61cb1b45a5e6a72ae4aaeb
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 12:07:27 2022 +0200
fix blend error and log parsing output
commit 1f751c2a039f9c97af57b18e0f019512631d5a25
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 10:33:33 2022 +0200
fix broken euler sampler
commit 02f8148d17efe4b6bde8d29b827092a0626363ee
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 10:24:20 2022 +0200
cleanup prompt parser
commit 8028d49ae6c16c0d6ec9c9de9c12d56c32201421
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Wed Oct 12 10:14:18 2022 +0200
explicit conjunction, improve flattening logic
commit 8a1710892185f07eb77483f7edae0fc4d6bbb250
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 22:59:30 2022 +0200
adapt multi-conditioning to also work with ddim
commit 53802a839850d0d1ff017c6bafe457c4bed750b0
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 22:31:42 2022 +0200
unconditioning is also fancy-prompt-syntaxable
commit 7c40892a9f184f7e216f14d14feb0411c5a90e24
Merge: e3f2dd6 dbe0da4
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 21:39:54 2022 +0200
Merge branch 'development-invoke' into fix-prompts
commit e3f2dd62b0548ca6988818ef058093a4f5b022f2
Merge: eef0e48 06f542e
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 21:38:09 2022 +0200
Merge remote-tracking branch 'upstream/development' into fix-prompts
commit eef0e484c2eaa1bd4e0e0b1d3f8d7bba38478144
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 21:26:25 2022 +0200
fix run-on paren-less attention, add some comments
commit fd29afdf0e9f5e0cdc60239e22480c36ca0aaeca
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 21:03:02 2022 +0200
python 3.9 compatibility
commit 26f7646eef7f39bc8f7ce805e747df0f723464da
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 20:58:42 2022 +0200
first pass connecting PromptParser to conditioning
commit ae53dff3796d7b9a5e7ed30fa1edb0374af6cd8d
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 20:51:15 2022 +0200
update frontend dist
commit 9be4a59a2d76f49e635474b5984bfca826a5dab4
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 19:01:39 2022 +0200
fix issues with correctness checking FlattenedPrompt
commit 3be212323eab68e72a363a654124edd9809e4cf0
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 18:43:16 2022 +0200
parsing nested seems to work pretty ok
commit acd73eb08cf67c27cac8a22934754321256f56a9
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 18:26:17 2022 +0200
wip introducing FlattenedPrompt class
commit 71698d5c7c2ac855b690d8ef67e8830148c59eda
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 15:59:42 2022 +0200
recursive attention weighting seems to actually work
commit a4e1ec6b20deb7cc0cd12737bdbd266e56144709
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 15:06:24 2022 +0200
now apparently almost supported nested attention
commit da76fd1ddf22a3888cdc08fd4fed38d8b178e524
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 11 13:23:37 2022 +0200
wip prompt parsing
commit dbe0da4572c2ac22f26a7afd722349a5680a9e47
Author: Kyle Schouviller <kyle0654@hotmail.com>
Date: Mon Oct 10 22:32:35 2022 -0700
Adding node-based invocation apps
commit 8f2a2ffc083366de74d7dae471b50b6f98a7c5f8
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Mon Oct 10 19:03:18 2022 +0200
fix merge issues
commit 73118dee2a8f4891700756e014caf1c9ca629267
Merge: fd00844 12413b0
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Mon Oct 10 12:42:48 2022 +0200
Merge remote-tracking branch 'upstream/development' into fix-prompts
commit fd0084413541013c2cf71e006af0392719bef53d
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Mon Oct 10 12:39:38 2022 +0200
wip prompt parsing
commit 0be9363db9307859d2b65cffc6af01f57d7873a4
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Mon Oct 10 03:20:06 2022 +0200
better +/- attention parsing
commit 5383f691874a58ab01cda1e4fac6cf330146526a
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Mon Oct 10 02:27:47 2022 +0200
prompt parser seems to work
commit 591d098a33ce35462428d8c169501d8ed73615ab
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 9 20:25:37 2022 +0200
supports weighting unconditioning, cross-attention with |
commit 7a7220563aa05a2980235b5b908362f66b728309
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 9 18:15:56 2022 +0200
i think cross attention might be working?
commit 951ed391e7126bff228c18b2db304ad28d59644a
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 9 16:04:54 2022 +0200
weighted CFG denoiser working with a single item
commit ee532a0c2827368c9e45a6a5f3975666402873da
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Sun Oct 9 06:33:40 2022 +0200
wip probably doesn't work or compile
commit 14654bcbd207b9ca28a6cbd37dbd967d699b062d
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 7 18:11:48 2022 +0200
use tan() to calculate embedding weight for <1 attentions
commit 1a8e76b31aa5abf5150419ebf3b29d4658d07f2b
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 7 16:14:54 2022 +0200
fix bad math.max reference
commit f697ff896875876ccaa1e5527405bdaa7ed27cde
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 7 15:55:57 2022 +0200
respect http[s]x protocol when making socket.io middleware
commit 41d3dd4eeae8d4efb05dfb44fc6d8aac5dc468ab
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 7 13:29:54 2022 +0200
fractional weighting works, by blending with prompts excluding the word
commit 087fb6dfb3e8f5e84de8c911f75faa3e3fa3553c
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 7 10:52:03 2022 +0200
wip doing weights <1 by averaging with conditioning absent the lower-weighted fragment
commit 3c49e3f3ec7c18dc60f3e18ed2f7f0d97aad3a47
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Fri Oct 7 10:36:15 2022 +0200
notate CFGDenoiser, perhaps
commit d2bcf1bb522026ebf209ad0103f6b370383e5070
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Thu Oct 6 05:04:47 2022 +0200
hack blending syntax to test attention weighting more extensively
commit 94904ef2cf917f74ec23ef7a570e12ff8255b048
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Thu Oct 6 04:56:37 2022 +0200
conditioning works, apparently
commit 7c6663ddd70f665fd1308b6dd74f92ca393a8df5
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Thu Oct 6 02:20:24 2022 +0200
attention weighting, definitely works in positive direction
commit 5856d453a9b020bc1a28ff643ae1f58c12c9be73
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 4 19:02:14 2022 +0200
wip bubbling weights down
commit a2ed14fd9b7d3cb36b6c5348018b364c76d1e892
Author: Damian at mba <damian@frey.NOSPAMco.nz>
Date: Tue Oct 4 17:35:39 2022 +0200
bring in changes from PC
test prompt:
"a cat sitting on a car {a dog sitting on a car}" -W 384 -H 256 -s 10 -S 12346 -A k_euler
note that substition of dog for cat is currently hard-coded (ksampler.py
line 43-44)
On the command line, the new option is --text_mask or -tm.
Example:
```
invoke> a baseball -I /path/to/still_life.png -tm orange
```
This will find the orange fruit in the still life painting and replace
it with an image of a baseball.
* fix mkdocs deployment
* update path to python bin
* add trigger for current branch
* change path to python_bin for mac as well
* try to use setup-python@v4 instead of setting env
* remove setup conda action
* try to use $CONDA
* remove overseen action
* change branch from master to main
* sort out if then else for faster syntax
* remove more if functions
* add updates to create-caches as well
* eliminate the rest of if functions
* try to unpin pytorch and torchvision
* restore pinned versions
* try switching from set-output to use env
* update test-invoke-conda as well
* fix env var creation
* quote variable
* add second equal to compare
* try another way to use outputs
* fix outputs
* pip install for mac before creating conda env
* fix output variable
* fix python bin path
* remove pip install for before creating conda env
* unpin streamlit version in conda mac env
* try to make git-workflows better readable
* remove 4gotten trigger
* Update-gh-actions (#6)
* fix mkdocs deployment
* update path to python bin
* add trigger for current branch
* change path to python_bin for mac as well
* try to use setup-python@v4 instead of setting env
* remove setup conda action
* try to use $CONDA
* remove overseen action
* change branch from master to main
* sort out if then else for faster syntax
* remove more if functions
* add updates to create-caches as well
* eliminate the rest of if functions
* try to unpin pytorch and torchvision
* restore pinned versions
* try switching from set-output to use env
* update test-invoke-conda as well
* fix env var creation
* quote variable
* add second equal to compare
* try another way to use outputs
* fix outputs
* pip install for mac before creating conda env
* fix output variable
* fix python bin path
* remove pip install for before creating conda env
* unpin streamlit version in conda mac env
* try to make git-workflows better readable
* use macos-latest
* try to update conda before creating mac env
* better conda update trial
* re-pin streamlit version
* re-added trigger to run workflow in current branch
* try to find out if conda mac env could be updated
* install cmake, protobuf and rust b4 conda
* add yes to conda update
* lets try anaconda3-2022.05
* try environment.yml for mac as well
* reenable conda mac env, add pip install
also fix gitignore by changing from dream to invoke
* remove
- unecesary virtualenv creation
- conda update
change != macos back to == linux
* remove cmake from brew install since pre-installed
* disable opencv-python pip requirement
* fixed commands to find latest package versions
* update requirements for mac env
* back to the roots - only install conda env
depending on runner_os with or without extra env variables
* check out macOS in azure-pipelines
since becoming kind of tired of the GitHub Runner which is broken as ...
* let's try to setup python and update conda env
* initialize conda before using it
* add trigger in azure-pipelines.yml
* And another go for update first ....
* update azure-pipelines.yml
- add caching
- add checkpoint download
- add paths to trigger
and more
* unquote checkpoint-url
* fix chekpoint-url variable
* mkdir before downloading model
* set pr trigger to main, rename anaconda cache
* unique cacheHitVariables
* try to use macos-latest instead of macos-12
* update test-invoke-conda.yml:
- remove unecesarry echo step
- use s-weigand/setup-conda@v1
- remove conda update from install deps step since updated with action
* update test-invoke-conda.yml:
- rename conda env cache from ldm to invokeai
- reorder steps:
1. checkout sources
2. setup python
3. setup conda
4. keep order after set platform variables
* change macos back to 12 since also fails with 11
* update condition in run the tests
make difference between main or not main
* fix path to cache invokeai conda env
* fix invokeai conda env cache path
* update mkdocs-flow.yml
* change conda-channel priority
* update create-caches
* update conda env also when cache was used
* os dependend conda env cache path
* use existing CONDA env pointing to conda root
* create CONDA_ROOT output from $CONDA
* use output variable to define test prompts
* use setup-python v4, get rid of PYTHON_BIN env
* add runner.os to result artifacts name
* update test-invoke-conda.yml:
- reuse macos-latest
- disable setup python 3.9
- setup conda with default python version
- create or update conda environment depending on cache success
- remove name parameter from conda update since name is set in env yml
* improve mkdocs-flow.yml
* disable cache-hugginface-torch
since preload_models.py downloads to more than one location
* update mkdocs-flow.yml with new name
* rename mkdocs action to mkdocs-material
* try to ignore error when creating conda env
maybe it would still be usable, lets see ;P
* remove bloat
* update environment-mac.yml
to match dependencies of invoke-ai/InvokeAI's main branch
* disable conda update, tweak prompt condition
* try to set some env vars for macOS to fix conda
* stop ignoring error, use env instead of outputs
* tweak `[[` connditions
* update python and pip dependencie
makes a difference of 1 sec per itteration compared to 3.9!!!
also I see no reason why using a old pip version would be beneficial
* remove unecesarry env for macOS
everything was pre-tested on my MacBook Air 2020 with M1
* update conda env in setup step
* activate conda env after installation
* update test-invoke-conda.yml
- set conda env dependent on matrix.os
- set CONDA_ENV_NAME to prevent breaking action when renaming conda env
- fix conda env activation
* fix activate conda env
* set bash -l as default shell
* use action to activate conda env
* add conda env file to env activation
* try to replace s-weigeand with conda-incubator
* remove azure-pipelines.yml
funniest part is that the macos runner is the same as the one on github!
* include environment-file in matrix
- also disable auto-activate-base and auto-update-conda
- include macos-latest and macos-12 for debugging purpose
- set miniforge-version in matrix
* fix miniforge-variant, set fail-fast to false
* add step to setup miniconda
- make default shell a matrix variable
- remove bloat
* use a mac env yml without pinned versions
* unpin nomkl, pytorch and torchvision
also removed opencv-pyhton
* cache conda pkgs dir instead of conda env
* use python 3.10, exclude macos-12 from cache
* fix expression
* prepare for PR
* fix doubled id
* reuse pinned versions in mac conda env
- updated python pip version
- unpined pytorch and torchvision
- removed opencv-python
- updated versions to most recent (tested locally)
* fix classical copy/paste error
* remove unused env from shell-block comment
* fix hashFiles function to determine restore-keys
* reenable caching `~.cache`, update create-caches
* unpin all versions in mac conda env file
this was the only way I got it working in the action, also works locally
tested on MacBook Air 2020 M1
remove environment-mac-unpinned.yml
* prepare merge by removing this branch from trigger
* include pull_request trigger for main and dev
* remove pull_request trigger
- In CLI: the argument is --png_compression <0..9> (-z<0..9>)
- In API, pass `compress_level` to PngWriter.save_image_and_prompt_to_png()
Compression ranges from 0 (no compression) to 9 (maximum compression).
Default value is 6 (as specified by Pillow package).
This addresses an issue first raised in #652.
* “Formally” means that there is a formality such as a rule or declaration, “formerly” refers to a prior state. The latter is almost certainly what is meant here.
On the command line, the new option is --text_mask or -tm.
Example:
```
invoke> a baseball -I /path/to/still_life.png -tm orange
```
This will find the orange fruit in the still life painting and replace
it with an image of a baseball.
* fix mkdocs deployment
* update path to python bin
* add trigger for current branch
* change path to python_bin for mac as well
* try to use setup-python@v4 instead of setting env
* remove setup conda action
* try to use $CONDA
* remove overseen action
* change branch from master to main
* sort out if then else for faster syntax
* remove more if functions
* add updates to create-caches as well
* eliminate the rest of if functions
* try to unpin pytorch and torchvision
* restore pinned versions
* try switching from set-output to use env
* update test-invoke-conda as well
* fix env var creation
* quote variable
* add second equal to compare
* try another way to use outputs
* fix outputs
* pip install for mac before creating conda env
* fix output variable
* fix python bin path
* remove pip install for before creating conda env
* unpin streamlit version in conda mac env
* try to make git-workflows better readable
* remove 4gotten trigger
* Update-gh-actions (#6)
* fix mkdocs deployment
* update path to python bin
* add trigger for current branch
* change path to python_bin for mac as well
* try to use setup-python@v4 instead of setting env
* remove setup conda action
* try to use $CONDA
* remove overseen action
* change branch from master to main
* sort out if then else for faster syntax
* remove more if functions
* add updates to create-caches as well
* eliminate the rest of if functions
* try to unpin pytorch and torchvision
* restore pinned versions
* try switching from set-output to use env
* update test-invoke-conda as well
* fix env var creation
* quote variable
* add second equal to compare
* try another way to use outputs
* fix outputs
* pip install for mac before creating conda env
* fix output variable
* fix python bin path
* remove pip install for before creating conda env
* unpin streamlit version in conda mac env
* try to make git-workflows better readable
* use macos-latest
* try to update conda before creating mac env
* better conda update trial
* re-pin streamlit version
* re-added trigger to run workflow in current branch
* try to find out if conda mac env could be updated
* install cmake, protobuf and rust b4 conda
* add yes to conda update
* lets try anaconda3-2022.05
* try environment.yml for mac as well
* reenable conda mac env, add pip install
also fix gitignore by changing from dream to invoke
* remove
- unecesary virtualenv creation
- conda update
change != macos back to == linux
* remove cmake from brew install since pre-installed
* disable opencv-python pip requirement
* fixed commands to find latest package versions
* update requirements for mac env
* back to the roots - only install conda env
depending on runner_os with or without extra env variables
* check out macOS in azure-pipelines
since becoming kind of tired of the GitHub Runner which is broken as ...
* let's try to setup python and update conda env
* initialize conda before using it
* add trigger in azure-pipelines.yml
* And another go for update first ....
* update azure-pipelines.yml
- add caching
- add checkpoint download
- add paths to trigger
and more
* unquote checkpoint-url
* fix chekpoint-url variable
* mkdir before downloading model
* set pr trigger to main, rename anaconda cache
* unique cacheHitVariables
* try to use macos-latest instead of macos-12
* update test-invoke-conda.yml:
- remove unecesarry echo step
- use s-weigand/setup-conda@v1
- remove conda update from install deps step since updated with action
* update test-invoke-conda.yml:
- rename conda env cache from ldm to invokeai
- reorder steps:
1. checkout sources
2. setup python
3. setup conda
4. keep order after set platform variables
* change macos back to 12 since also fails with 11
* update condition in run the tests
make difference between main or not main
* fix path to cache invokeai conda env
* fix invokeai conda env cache path
* update mkdocs-flow.yml
* change conda-channel priority
* update create-caches
* update conda env also when cache was used
* os dependend conda env cache path
* use existing CONDA env pointing to conda root
* create CONDA_ROOT output from $CONDA
* use output variable to define test prompts
* use setup-python v4, get rid of PYTHON_BIN env
* add runner.os to result artifacts name
* update test-invoke-conda.yml:
- reuse macos-latest
- disable setup python 3.9
- setup conda with default python version
- create or update conda environment depending on cache success
- remove name parameter from conda update since name is set in env yml
* improve mkdocs-flow.yml
* disable cache-hugginface-torch
since preload_models.py downloads to more than one location
* update mkdocs-flow.yml with new name
* rename mkdocs action to mkdocs-material
* try to ignore error when creating conda env
maybe it would still be usable, lets see ;P
* remove bloat
* update environment-mac.yml
to match dependencies of invoke-ai/InvokeAI's main branch
* disable conda update, tweak prompt condition
* try to set some env vars for macOS to fix conda
* stop ignoring error, use env instead of outputs
* tweak `[[` connditions
* update python and pip dependencie
makes a difference of 1 sec per itteration compared to 3.9!!!
also I see no reason why using a old pip version would be beneficial
* remove unecesarry env for macOS
everything was pre-tested on my MacBook Air 2020 with M1
* update conda env in setup step
* activate conda env after installation
* update test-invoke-conda.yml
- set conda env dependent on matrix.os
- set CONDA_ENV_NAME to prevent breaking action when renaming conda env
- fix conda env activation
* fix activate conda env
* set bash -l as default shell
* use action to activate conda env
* add conda env file to env activation
* try to replace s-weigeand with conda-incubator
* remove azure-pipelines.yml
funniest part is that the macos runner is the same as the one on github!
* include environment-file in matrix
- also disable auto-activate-base and auto-update-conda
- include macos-latest and macos-12 for debugging purpose
- set miniforge-version in matrix
* fix miniforge-variant, set fail-fast to false
* add step to setup miniconda
- make default shell a matrix variable
- remove bloat
* use a mac env yml without pinned versions
* unpin nomkl, pytorch and torchvision
also removed opencv-pyhton
* cache conda pkgs dir instead of conda env
* use python 3.10, exclude macos-12 from cache
* fix expression
* prepare for PR
* fix doubled id
* reuse pinned versions in mac conda env
- updated python pip version
- unpined pytorch and torchvision
- removed opencv-python
- updated versions to most recent (tested locally)
* fix classical copy/paste error
* remove unused env from shell-block comment
* fix hashFiles function to determine restore-keys
* reenable caching `~.cache`, update create-caches
* unpin all versions in mac conda env file
this was the only way I got it working in the action, also works locally
tested on MacBook Air 2020 M1
remove environment-mac-unpinned.yml
* prepare merge by removing this branch from trigger
* include pull_request trigger for main and dev
* remove pull_request trigger
* fix mkdocs deployment
* update path to python bin
* add trigger for current branch
* change path to python_bin for mac as well
* try to use setup-python@v4 instead of setting env
* remove setup conda action
* try to use $CONDA
* remove overseen action
* change branch from master to main
* sort out if then else for faster syntax
* remove more if functions
* add updates to create-caches as well
* eliminate the rest of if functions
* try to unpin pytorch and torchvision
* restore pinned versions
* try switching from set-output to use env
* update test-invoke-conda as well
* fix env var creation
* quote variable
* add second equal to compare
* try another way to use outputs
* fix outputs
* pip install for mac before creating conda env
* fix output variable
* fix python bin path
* remove pip install for before creating conda env
* unpin streamlit version in conda mac env
* try to make git-workflows better readable
* remove 4gotten trigger
* Update-gh-actions (#6)
* fix mkdocs deployment
* update path to python bin
* add trigger for current branch
* change path to python_bin for mac as well
* try to use setup-python@v4 instead of setting env
* remove setup conda action
* try to use $CONDA
* remove overseen action
* change branch from master to main
* sort out if then else for faster syntax
* remove more if functions
* add updates to create-caches as well
* eliminate the rest of if functions
* try to unpin pytorch and torchvision
* restore pinned versions
* try switching from set-output to use env
* update test-invoke-conda as well
* fix env var creation
* quote variable
* add second equal to compare
* try another way to use outputs
* fix outputs
* pip install for mac before creating conda env
* fix output variable
* fix python bin path
* remove pip install for before creating conda env
* unpin streamlit version in conda mac env
* try to make git-workflows better readable
* use macos-latest
* try to update conda before creating mac env
* better conda update trial
* re-pin streamlit version
* re-added trigger to run workflow in current branch
* try to find out if conda mac env could be updated
* install cmake, protobuf and rust b4 conda
* add yes to conda update
* lets try anaconda3-2022.05
* try environment.yml for mac as well
* reenable conda mac env, add pip install
also fix gitignore by changing from dream to invoke
* remove
- unecesary virtualenv creation
- conda update
change != macos back to == linux
* remove cmake from brew install since pre-installed
* disable opencv-python pip requirement
* fixed commands to find latest package versions
* update requirements for mac env
* back to the roots - only install conda env
depending on runner_os with or without extra env variables
* check out macOS in azure-pipelines
since becoming kind of tired of the GitHub Runner which is broken as ...
* let's try to setup python and update conda env
* initialize conda before using it
* add trigger in azure-pipelines.yml
* And another go for update first ....
* update azure-pipelines.yml
- add caching
- add checkpoint download
- add paths to trigger
and more
* unquote checkpoint-url
* fix chekpoint-url variable
* mkdir before downloading model
* set pr trigger to main, rename anaconda cache
* unique cacheHitVariables
* try to use macos-latest instead of macos-12
* update test-invoke-conda.yml:
- remove unecesarry echo step
- use s-weigand/setup-conda@v1
- remove conda update from install deps step since updated with action
* update test-invoke-conda.yml:
- rename conda env cache from ldm to invokeai
- reorder steps:
1. checkout sources
2. setup python
3. setup conda
4. keep order after set platform variables
* change macos back to 12 since also fails with 11
* update condition in run the tests
make difference between main or not main
* fix path to cache invokeai conda env
* fix invokeai conda env cache path
* update mkdocs-flow.yml
* change conda-channel priority
* update create-caches
* update conda env also when cache was used
* os dependend conda env cache path
* use existing CONDA env pointing to conda root
* create CONDA_ROOT output from $CONDA
* use output variable to define test prompts
* use setup-python v4, get rid of PYTHON_BIN env
* add runner.os to result artifacts name
* update test-invoke-conda.yml:
- reuse macos-latest
- disable setup python 3.9
- setup conda with default python version
- create or update conda environment depending on cache success
- remove name parameter from conda update since name is set in env yml
* improve mkdocs-flow.yml
* disable cache-hugginface-torch
since preload_models.py downloads to more than one location
* update mkdocs-flow.yml with new name
* rename mkdocs action to mkdocs-material
* try to ignore error when creating conda env
maybe it would still be usable, lets see ;P
* remove bloat
* update environment-mac.yml
to match dependencies of invoke-ai/InvokeAI's main branch
* disable conda update, tweak prompt condition
* try to set some env vars for macOS to fix conda
* stop ignoring error, use env instead of outputs
* tweak `[[` connditions
* update python and pip dependencie
makes a difference of 1 sec per itteration compared to 3.9!!!
also I see no reason why using a old pip version would be beneficial
* remove unecesarry env for macOS
everything was pre-tested on my MacBook Air 2020 with M1
* update conda env in setup step
* activate conda env after installation
* update test-invoke-conda.yml
- set conda env dependent on matrix.os
- set CONDA_ENV_NAME to prevent breaking action when renaming conda env
- fix conda env activation
* fix activate conda env
* set bash -l as default shell
* use action to activate conda env
* add conda env file to env activation
* try to replace s-weigeand with conda-incubator
* remove azure-pipelines.yml
funniest part is that the macos runner is the same as the one on github!
* include environment-file in matrix
- also disable auto-activate-base and auto-update-conda
- include macos-latest and macos-12 for debugging purpose
- set miniforge-version in matrix
* fix miniforge-variant, set fail-fast to false
* add step to setup miniconda
- make default shell a matrix variable
- remove bloat
* use a mac env yml without pinned versions
* unpin nomkl, pytorch and torchvision
also removed opencv-pyhton
* cache conda pkgs dir instead of conda env
* use python 3.10, exclude macos-12 from cache
* fix expression
* prepare for PR
* fix doubled id
* reuse pinned versions in mac conda env
- updated python pip version
- unpined pytorch and torchvision
- removed opencv-python
- updated versions to most recent (tested locally)
* fix classical copy/paste error
* remove unused env from shell-block comment
* fix hashFiles function to determine restore-keys
* reenable caching `~.cache`, update create-caches
* unpin all versions in mac conda env file
this was the only way I got it working in the action, also works locally
tested on MacBook Air 2020 M1
remove environment-mac-unpinned.yml
* prepare merge by removing this branch from trigger
* include pull_request trigger for main and dev
* remove pull_request trigger
<div> around the inline images works great in gh-pages, but breaks plain old markdown in GitHub code display. This removes the <div>s, causing slight degradation in quality of gh-page appearance.
- In CLI: the argument is --png_compression <0..9> (-z<0..9>)
- In API, pass `compress_level` to PngWriter.save_image_and_prompt_to_png()
Compression ranges from 0 (no compression) to 9 (maximum compression).
Default value is 6 (as specified by Pillow package).
This addresses an issue first raised in #652.
- --inpaint_replace 0.X will cause inpainting to ignore what is under
the masked region with a strength ranging from 0 (don't ignore at all)
to 1.0 (ignore completely)
- sync with upstream development
- update docs
- add a `--inpaint_replace` option that fills masked regions with
latent noise. This allows radical changes to inpainted regions
at the cost of losing context.
- fix up readline, arg processing and metadata writing to accommodate
this change
- fixed bug in storage and retrieval of variations, discovered incidentally
during testing
- update documentation
- Error checks for invalid model
- Add !del_model command to invoke.py
- Add del_model() method to model_cache
- Autocompleter kept in sync with model addition/subtraction.
At step counts greater than ~75, the ksamplers start producing noisy
images when using the Karras noise schedule. This PR reverts to using
the model's own noise schedule, which eliminates the problem at the
cost of slowing convergence at lower step counts.
This PR also introduces a new CLI `--save_intermediates <n>' argument,
which will save every nth intermediate image into a subdirectory
named `intermediates/<image_prefix>'.
Addresses issue #1083.
At step counts greater than ~75, the ksamplers start producing noisy
images when using the Karras noise schedule. This PR reverts to using
the model's own noise schedule, which eliminates the problem at the
cost of slowing convergence at lower step counts.
This PR also introduces a new CLI `--save_intermediates <n>' argument,
which will save every nth intermediate image into a subdirectory
named `intermediates/<image_prefix>'.
Addresses issue #1083.
- !import_model <path/to/model/weights> will import a new model,
prompt the user for its name and description, write it to the
models.yaml file, and load it.
- !edit_model <model_name> will bring up a previously-defined model
and prompt the user to edit its descriptive fields.
Example of !import_model
<pre>
invoke> <b>!import_model models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt</b>
>> Model import in process. Please enter the values needed to configure this model:
Name for this model: <b>waifu-diffusion</b>
Description of this model: <b>Waifu Diffusion v1.3</b>
Configuration file for this model: <b>configs/stable-diffusion/v1-inference.yaml</b>
Default image width: <b>512</b>
Default image height: <b>512</b>
>> New configuration:
waifu-diffusion:
config: configs/stable-diffusion/v1-inference.yaml
description: Waifu Diffusion v1.3
height: 512
weights: models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
width: 512
OK to import [n]? <b>y</b>
>> Caching model stable-diffusion-1.4 in system RAM
>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
| LatentDiffusion: Running in eps-prediction mode
| DiffusionWrapper has 859.52 M params.
| Making attention of type 'vanilla' with 512 in_channels
| Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
| Making attention of type 'vanilla' with 512 in_channels
| Using faster float16 precision
</pre>
Example of !edit_model
<pre>
invoke> <b>!edit_model waifu-diffusion</b>
>> Editing model waifu-diffusion from configuration file ./configs/models.yaml
description: <b>Waifu diffusion v1.4beta</b>
weights: models/ldm/stable-diffusion-v1/<b>model-epoch10-float16.ckpt</b>
config: configs/stable-diffusion/v1-inference.yaml
width: 512
height: 512
>> New configuration:
waifu-diffusion:
config: configs/stable-diffusion/v1-inference.yaml
description: Waifu diffusion v1.4beta
weights: models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
height: 512
width: 512
OK to import [n]? y
>> Caching model stable-diffusion-1.4 in system RAM
>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch10-float16.ckpt
...
</pre>
This commit "reverts" the new API changes by extracting the old
functionality into new files.
The work is based on the commit `803a51d5adca7e6e28491fc414fd3937bee7cb79`
PngWriter regained PromptFormatter as old server used that.
`server_legacy.py` is the old server that `dream.py` used.
Finally `legacy_api.py` is what `dream.py` used to be at the mentioned
commit.
One manually run test has been added in order to be able to test
compatibility with the old API, currently just testing that the API
endpoint works the same way + the image hash is the same as it used to
be before.
- This PR enables two new commands in the invoke.py script
!models -- list the available models and their cache status
!switch <model> -- switch to the indicated model
Example:
invoke> !models
laion400m not loaded Latent Diffusion LAION400M model
stable-diffusion-1.4 active Stable Diffusion inference model version 1.4
waifu-1.3 cached Waifu anime model version 1.3
invoke> !switch waifu-1.3
>> Caching model stable-diffusion-1.4 in system RAM
>> Retrieving model waifu-1.3 from system RAM cache
The name and descriptions of the models are taken from
`config/models.yaml`. A future enhancement to `model_cache.py` will be
to enable new model stanzas to be added to the file
programmatically. This will be useful for the WebGUI.
More details:
- Use fast switching algorithm described in PR #948
- Models are selected using their configuration stanza name
given in models.yaml.
- To avoid filling up CPU RAM with cached models, this PR
implements an LRU cache that monitors available CPU RAM.
- The caching code allows the minimum value of available RAM
to be adjusted, but invoke.py does not currently have a
command-line argument that allows you to set it. The
minimum free RAM is arbitrarily set to 2 GB.
- Add optional description field to configs/models.yaml
Unrelated fixes:
- Added ">>" to CompViz model loading messages in order to make user experience
more consistent.
- When generating an image greater than defaults, will only warn about possible
VRAM filling the first time.
- Fixed bug that was causing help message to be printed twice. This involved
moving the import line for the web backend into the section where it is
called.
Coauthored by: @ArDiouscuros
- This PR enables two new commands in the invoke.py script
!models -- list the available models and their cache status
!switch <model> -- switch to the indicated model
Example:
invoke> !models
laion400m not loaded Latent Diffusion LAION400M model
stable-diffusion-1.4 active Stable Diffusion inference model version 1.4
waifu-1.3 cached Waifu anime model version 1.3
invoke> !switch waifu-1.3
>> Caching model stable-diffusion-1.4 in system RAM
>> Retrieving model waifu-1.3 from system RAM cache
More details:
- Use fast switching algorithm described in PR #948
- Models are selected using their configuration stanza name
given in models.yaml.
- To avoid filling up CPU RAM with cached models, this PR
implements an LRU cache that monitors available CPU RAM.
- The caching code allows the minimum value of available RAM
to be adjusted, but invoke.py does not currently have a
command-line argument that allows you to set it. The
minimum free RAM is arbitrarily set to 2 GB.
- Add optional description field to configs/models.yaml
Unrelated fixes:
- Added ">>" to CompViz model loading messages in order to make user experience
more consistent.
- When generating an image greater than defaults, will only warn about possible
VRAM filling the first time.
- Fixed bug that was causing help message to be printed twice. This involved
moving the import line for the web backend into the section where it is
called.
- better readability in dark mode since color change
- better looking changelog
- fix images which where not loading
- also center most of the images
- fix some syntax errors like
- headlines ending with a colon
- codeblocks with wrong fences
- codeblocks without shell
- update conda prompts from ldm to invokeai
- ....
- the prompt argument comes before the optional arguments
- usage statement shows 'invoke>' rather than 'invoke.py'
- use pydoc pager to help display long help message
- the prompt argument comes before the optional arguments
- usage statement shows 'invoke>' rather than 'invoke.py'
- use pydoc pager to help display long help message
- rename dream.py to invoke.py
- create a compatibility script named dream.py that execs() invoke.py
- redo documentation
- change help message in args
- this does **not** rename the libraries, which are still ldm.dream.util, etc
This reverts commit 5f42d08945.
This fix was intended to solve issue #939, in which ESRGAN generates
dark images when upscaling 4X on certain GTX cards. However, the fix
apparently causes conflicts with some versions of the ESRGAN library,
and this fix will have to wait until after release of 2.0.
- txt2img2img back to using DDIM as img2img sampler; results produced
by some k* samplers are just not reliable enough for good user
experience
- img2img progress message clarifies why img2img steps taken != steps requested
- warn of potential problems when user tries to run img2img on a small init image
- updated environment-mac.yml #932
- use the upstream GFPGAN library now that issues with color-changing fixed
and facial recognition improved #905
- preload_models fixed to download additional models needed by gfpgan
- Added support for pyreadline3 so that Window users can benefit.
- Added the !search command to search the history for a matching string:
~~~
!search puppies
[20] puppies at the food bowl -Ak_lms
[54] house overrun by hungry puppies -C20 -s100
~~~
- Added the !clear command to clear the in-memory and on-disk
command history.
- embiggen needs to use ddim sampler due to low step count
- --hires_fix option needs to be written to log and command string
- fix call signature of _init_image_mask()
- When generating multiple images, the first seed was being used for second
and subsequent files. This should only happen when variations are being
generated. Now fixed.
- img2img confirmed working with all samplers
- inpainting working on ddim & plms. Changes to k-diffusion
module seem to be needed for inpainting support.
- switched k-diffuser noise schedule to original karras schedule,
which reduces the step number needed for good results
-if readline.set_auto_history() is not implemented, as in pyreadline3, will fall
back gracefully to automatic history saving. The only issue with this is that
-!history commands will be recorded in the history.
-!fetch on missing file no longer crashes script
-!history is now one of the autocomplete commands
-.dream_history now stored in output directory rather than ~user directory.
An important limitation of the last feature is that the history is
loaded and saved to the .dream_history file in the --outdir directory
specified at script launch time. It is not swapped around when the
--outdir is changed during the session.
Add message about interpolation size
Fix crash if sampler not set to DDIM, change parameter name to hires_fix
Hi res mode fix duplicates with img2img scaling
Add message about interpolation size
Fix crash if sampler not set to DDIM, change parameter name to hires_fix
Hi res mode fix duplicates with img2img scaling
-if readline.set_auto_history() is not implemented, as in pyreadline3, will fall
back gracefully to automatic history saving. The only issue with this is that
-!history commands will be recorded in the history.
-!fetch on missing file no longer crashes script
-!history is now one of the autocomplete commands
-.dream_history now stored in output directory rather than ~user directory.
An important limitation of the last feature is that the history is
loaded and saved to the .dream_history file in the --outdir directory
specified at script launch time. It is not swapped around when the
--outdir is changed during the session.
- When --save_orig *not* provided during image generation with
upscaling/face fixing, an extra image file was being created. This
PR fixes the problem.
- Also generalizes the tab autocomplete for image paths such that
autocomplete searches the output directory for all path-modifying
options except for --outdir.
- normalized how filenames are written out when postprocessing invoked
- various fixes of bugs encountered during testing
- updated documentation
- updated help text
- Enhance tab completion functionality
- Each of the switches that read a filepath (e.g. --init_img) will trigger file path completion. The
-S switch will display a list of recently-used seeds.
- Added new !fetch command to retrieve the metadata from a previously-generated image and populate the
readline linebuffer with the appropriate editable command to regenerate.
- Added new !history command to display previous commands and reload them for modification.
- The !fetch and !fix commands both autocomplete *and* search automatically through the current
outdir for files.
- The completer maintains a list of recently used seeds and will try to autocomplete them.
- normalized how filenames are written out when postprocessing invoked
- various fixes of bugs encountered during testing
- updated documentation
- updated help text
- Enhance tab completion functionality
- Each of the switches that read a filepath (e.g. --init_img) will trigger file path completion. The
-S switch will display a list of recently-used seeds.
- Added new !fetch command to retrieve the metadata from a previously-generated image and populate the
readline linebuffer with the appropriate editable command to regenerate.
- Added new !history command to display previous commands and reload them for modification.
- The !fetch and !fix commands both autocomplete *and* search automatically through the current
outdir for files.
- The completer maintains a list of recently used seeds and will try to autocomplete them.
- args.py will now attempt to return a metadata-containing Args
object using the following methods:
1. By looking for the 'sd-metadata' tag in the PNG info
2. By looking from the 'Dream' tag
3. As a last resort, fetch the seed from the filename and assume
defaults for all other options.
Pin `openh264` to 2.3.0 until OpenCV supports 2.3.1 or newer. Added just to `environment-mac.yml` since I know this happens on M1 / Apple Silicon Macs (running macOS 13) and that's all I can test on.
Either Huggingface's 'transformers' lib introduced a regression in v4.22, or we changed how we're using 'transformers' in such a way that we break when using v4.22.
Pin to 'transformers==4.21.*'
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
In the case of this "point", the Warp Terminal cannot be clicked directly to trigger the browser to open, and Chrome is a blank page. It should open properly once you remove it
Build the base generator in same place and way as other generators to reduce the chance of missed arguments in the future.
Fixes crash with display in-progress images, though note the feature still doesn't work for other reasons.
- For unknown reasons, conda removes the base directory from the path
on Macintoshes when pyproject.toml is present (even if the file is
empty). This commit renames pyproject.toml to pyproject.toml.hide
until the issue is understood better.
1. Add ldm/dream/restoration/__init__.py file that was inadvertently not
committed earlier.
2. Add '.' to sys.path to address weird mac problem reported in #723
- Adapted from PR #489, author Dominic Letz [https://github.com/dominicletz]
- Too many upstream changes to merge, so frankensteined it in.
- Added support for !fix syntax
- Added documentation
- The seed printed needs to be the one generated prior to the
initial noising operation. To do this, I added a new "first_seed"
argument to the image callback in dream.py.
- Closes#641
- modify strength of embiggen to reduce tiling ghosts
- normalize naming of postprocessed files (could improve more to avoid
name collisions)
- move restoration modules under ldm.dream
- supports gfpgan, esrgan, codeformer and embiggen
- To use:
dream> !fix ./outputs/img-samples/000056.292144555.png -ft gfpgan -U2 -G0.8
dream> !fix ./outputs/img-samples/000056.292144555.png -ft codeformer -G 0.8
dream> !fix ./outputs/img-samples/000056.29214455.png -U4
dream> !fix ./outputs/img-samples/000056.292144555.png -embiggen 1.5
The first example invokes gfpgan to fix faces and esrgan to upscale.
The second example invokes codeformer to fix faces, no upscaling
The third example uses esrgan to upscale 4X
The four example runs embiggen to enlarge 1.5X
- This is very preliminary work. There are some anomalies to note:
1. The syntax is non-obvious. I would prefer something like:
!fix esrgan,gfpgan
!fix esrgan
!fix embiggen,codeformer
However, this will require refactoring the gfpgan and embiggen
code.
2. Images generated using gfpgan, esrgan or codeformer all are named
"xxxxxx.xxxxxx.postprocessed.png" and the original is saved.
However, the prefix is a new one that is not related to the
original.
3. Images generated using embiggen are named "xxxxx.xxxxxxx.png",
and once again the prefix is new. I'm not sure whether the
prefix should be aligned with the original file's prefix or not.
Probably not, but opinions welcome.
Please don't make me keep having to cclean this up
1) Centering of the front matter is completely wrecked
2) We are not a billboard for Discord. We have a perfectly good badge - if the *link* needs fixing, fix it.
3) Stop putting HTML in Markdown
4) We need to state who and what we are once, clearly, not 3 times...
- <b>InvokeAI: A Stable Diffusion Toolkit</b>
- # Stable Diffusion Dream Script
- # **InvokeAI - A Stable Diffusion Toolkit**
5) Headings in Markdown SHOULD NOT HAVE additional formatting
Allowed values are 'auto', 'float32', 'autocast', 'float16'. If not specified or 'auto' a working precision is automatically selected based on the torch device.
Context: #526
Deprecated --full_precision / -F
Tested on both cuda and cpu by calling scripts/dream.py without arguments and checked the auto configuration worked. With --precision=auto/float32/autocast/float16 it performs as expected, either working or failing with a reasonable error. Also checked Img2Img.
1. let users install Rust right at the beginning in order to avoid some troubleshooting later on
2. add "conda deactivate" for troubleshooting once ldm was activated
Fix conflict
Update INSTALL_MAC.md
- modify strength of embiggen to reduce tiling ghosts
- normalize naming of postprocessed files (could improve more to avoid
name collisions)
- move restoration modules under ldm.dream
- supports gfpgan, esrgan, codeformer and embiggen
- To use:
dream> !fix ./outputs/img-samples/000056.292144555.png -ft gfpgan -U2 -G0.8
dream> !fix ./outputs/img-samples/000056.292144555.png -ft codeformer -G 0.8
dream> !fix ./outputs/img-samples/000056.29214455.png -U4
dream> !fix ./outputs/img-samples/000056.292144555.png -embiggen 1.5
The first example invokes gfpgan to fix faces and esrgan to upscale.
The second example invokes codeformer to fix faces, no upscaling
The third example uses esrgan to upscale 4X
The four example runs embiggen to enlarge 1.5X
- This is very preliminary work. There are some anomalies to note:
1. The syntax is non-obvious. I would prefer something like:
!fix esrgan,gfpgan
!fix esrgan
!fix embiggen,codeformer
However, this will require refactoring the gfpgan and embiggen
code.
2. Images generated using gfpgan, esrgan or codeformer all are named
"xxxxxx.xxxxxx.postprocessed.png" and the original is saved.
However, the prefix is a new one that is not related to the
original.
3. Images generated using embiggen are named "xxxxx.xxxxxxx.png",
and once again the prefix is new. I'm not sure whether the
prefix should be aligned with the original file's prefix or not.
Probably not, but opinions welcome.
fix double bs python path in cli.md and fix tables again
add more keys in cli.md
fix annotations in install_mac.md
remove torchaudio from pythorch-nightly installation
fix self reference
- supports gfpgan, esrgan, codeformer and embiggen
- To use:
dream> !fix ./outputs/img-samples/000056.292144555.png -ft gfpgan -U2 -G0.8
dream> !fix ./outputs/img-samples/000056.292144555.png -ft codeformer -G 0.8
dream> !fix ./outputs/img-samples/000056.29214455.png -U4
dream> !fix ./outputs/img-samples/000056.292144555.png -embiggen 1.5
The first example invokes gfpgan to fix faces and esrgan to upscale.
The second example invokes codeformer to fix faces, no upscaling
The third example uses esrgan to upscale 4X
The four example runs embiggen to enlarge 1.5X
- This is very preliminary work. There are some anomalies to note:
1. The syntax is non-obvious. I would prefer something like:
!fix esrgan,gfpgan
!fix esrgan
!fix embiggen,codeformer
However, this will require refactoring the gfpgan and embiggen
code.
2. Images generated using gfpgan, esrgan or codeformer all are named
"xxxxxx.xxxxxx.postprocessed.png" and the original is saved.
However, the prefix is a new one that is not related to the
original.
3. Images generated using embiggen are named "xxxxx.xxxxxxx.png",
and once again the prefix is new. I'm not sure whether the
prefix should be aligned with the original file's prefix or not.
Probably not, but opinions welcome.
* Support color correction for img2img and inpainting, avoiding the shift to magenta seen when running images through img2img repeatedly.
* Fix docs for color correction
* add --init_color to prompt reconstruction
* For best results, the --init_color option should point to the *very first* image used in the sequence of img2img operations. Otherwise color correction will skew towards cyan.
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
- use git-revision-date-localized with enabled creation date
- update requirements-mkdocs.txt and pin verisons
- add requirements
- add dev addr
- fix template
- use better icons for repo and edit button
- remove odd extension
disabled toc in order to view those large tables
added linebreaks in long cells to stop multiline arguments/shortcut
added backticks arround arguments to stop interpreting `<...>` as html
added missing identifiers to codeblocks
changed html tags to markdown to insert the png
Fixes:
File "stable-diffusion/ldm/modules/diffusionmodules/model.py", line 37, in nonlinearity
return x*torch.sigmoid(x)
RuntimeError: CUDA out of memory. Tried to allocate 1.56 GiB [..]
Now up to 1536x1280 is possible on 8GB VRAM.
Also remove unused SiLU class.
* Added linux to the workflows
- rename workflow files
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* fixes: run on merge to 'main', 'dev';
- reduce dev merge test cases to 1 (1 takes 11 minutes 😯)
- fix model cache name
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* add test prompts to workflows
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
Co-authored-by: James Reynolds <magnsuviri@me.com>
Apply ~6% speedup by moving * self.scale to earlier on a smaller tensor.
When we have enough VRAM don't make a useless zeros tensor.
Switch between cuda/mps/cpu based on q.device.type to allow cleaner per architecture future optimizations.
For cuda and cpu keep VRAM usage and faster slicing consistent.
For cpu use smaller slices. Tested ~20% faster on i7, 9.8 to 7.7 s/it.
Fix = typo to self.mem_total >= 8 in einsum_op_mps_v2 as per #582 discussion.
- fixes no closing quote in pretty-printed dream_prompt string
- removes unecessary -f switch when txt2img used
In addition, this commit does an experimental commenting-out of the
random.seed() call in the variation-generating part of ldm.dream.generator.base.
This fixes the problem of two calls that use the same seed and -v0.1
generating different images (#641). However, it does not fix the issue
of two images generated using the same seed and -VXXXXXX being
different.
- switch badge service to badgen, as I couldn't figure out shields.io
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* Added linux to the workflows
- rename workflow files
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* fixes: run on merge to 'main', 'dev';
- reduce dev merge test cases to 1 (1 takes 11 minutes 😯)
- fix model cache name
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* add test prompts to workflows
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
Co-authored-by: James Reynolds <magnsuviri@me.com>
Co-authored-by: Ben Alkov <ben.alkov@gmail.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
* due to changes in the metadata written to PNG files, web server cannot
display images
* issue is identified and will be fixed in next 24h
* Python 3.9 required for flask/react web server; environment must be
updated.
* Implements rudimentary api
* Fixes blocking in API
* Adds UI to monorepo > src/frontend/
* Updates frontend/README
* Reverts conda env name to `ldm`
* Fixes environment yamls
* CORS config for testing
* Fixes LogViewer position
* API WID
* Adds actions to image viewer
* Increases vite chunkSizeWarningLimit to 1500
* Implements init image
* Implements state persistence in localStorage
* Improve progress data handling
* Final build
* Fixes mimetypes error on windows
* Adds error logging
* Fixes bugged img2img strength component
* Adds sourcemaps to dev build
* Fixes missing key
* Changes connection status indicator to text
* Adds ability to serve other hosts than localhost
* Adding Flask API server
* Removes source maps from config
* Fixes prop transfer
* Add missing packages and add CORS support
* Adding API doc
* Remove defaults from openapi doc
* Adds basic error handling for server config query
* Mostly working socket.io implementation.
* Fixes bug preventing mask upload
* Fixes bug with sampler name not written to metadata
* UI Overhaul, numerous fixes
Co-authored-by: Kyle Schouviller <kyle0654@hotmail.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
* Feature complete for #266 with exception of several small deviations:
1. initial image and model weight hashes use full sha256 hash rather than first 8 digits
2. Initialization parameters for post-processing steps not provided
3. Uses top-level "images" tags for both a single image and a grid of images. This change was suggested in a comment.
* Added scripts/sd_metadata.py to retrieve and print metadata from PNG files
* New ldm.dream.args.Args class is a namespace like object which holds all defaults and can be modified during exection to hold current settings.
* Modified dream.py and server.py to accommodate Args class.
This change makes it so any API clients can show the same error as what
happens in the terminal where you run the API. Useful for various WebUIs
to display more helpful error messages to users.
Co-authored-by: CapableWeb <capableweb@domain.com>
* Refactor generate.py and dream.py
* config file path (models.yaml) is parsed inside Generate() to simplify
API
* Better handling of keyboard interrupts in file loading mode vs
interactive
* Removed oodles of unused variables.
* move nonfunctional inpainting out of the scripts directory
* fix ugly ddim tqdm formatting
* fix embiggen breakage, formatting fixes
* fix web server handling of rel and abs outdir paths
* Can now specify either a relative or absolute path for outdir
* Outdir path does not need to be inside the stable-diffusion directory
* Closes security hole that allowed user to read any file within
stable-diffusion (eek!)
* Closes#536
* revert inadvertent change of conda env name (#528)
* Refactor generate.py and dream.py
* config file path (models.yaml) is parsed inside Generate() to simplify
API
* Better handling of keyboard interrupts in file loading mode vs
interactive
* Removed oodles of unused variables.
* move nonfunctional inpainting out of the scripts directory
* fix ugly ddim tqdm formatting
* Refactor pip requirements across the board
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* fix name, version in setup.py
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* Update notebooks for new requirements file changes
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* slightly more consistent in how the different scenarios are described
* moved the stuff about `/usr/bin/python` to be adjacent to the stuff about `/usr/bin/python3`
* added an example of the 'option 1' goal state
* described a way to directly answer the question: how many snakes are living in your computer?
Code cleanup and attention.py einsum_ops update for M1 16-32GB performance.
Expected: On par with fastest ever from 8 to 128GB for 512x512. Allows large images.
When running on just cpu (intel), a call to torch.layer_norm would error with RuntimeError: expected scalar type BFloat16 but found Float
Fix buggy device handling in model.py.
Tested with scripts/dream.py --full_precision on just cpu on intel laptop. Works but slow at ~10s/it.
* Add Embiggen automation
* Make embiggen_tiles masking more intelligent and count from one (at least for the user), rewrite sections of Embiggen README, fix various typos throughout README
* drop duplicate log message
commit 1c649e4663
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 12 13:29:16 2022 -0400
fix torchvision dependency version #511
commit 4d197f699e
Merge: a3e07fb190ba78
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 12 07:29:19 2022 -0400
Merge branch 'development' of github.com:lstein/stable-diffusion into development
commit a3e07fb84a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 12 07:28:58 2022 -0400
fix grid crash
commit 9fa1f31bf2
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 12 07:07:05 2022 -0400
fix opencv and realesrgan dependencies in mac install
commit 190ba78960
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 12 01:50:58 2022 -0400
Update requirements-mac.txt
Fixed dangling dash on last line.
commit 25d9ccc509
Author: Any-Winter-4079 <50542132+Any-Winter-4079@users.noreply.github.com>
Date: Mon Sep 12 03:17:29 2022 +0200
Update model.py
commit 9cdf3aca7d
Author: Any-Winter-4079 <50542132+Any-Winter-4079@users.noreply.github.com>
Date: Mon Sep 12 02:52:36 2022 +0200
Update attention.py
Performance improvements to generate larger images in M1 #431
Update attention.py
Added dtype=r1.dtype to softmax
commit 49a96b90d8
Author: Mihai <299015+mh-dm@users.noreply.github.com>
Date: Sat Sep 10 16:58:07 2022 +0300
~7% speedup (1.57 to 1.69it/s) from switch to += in ldm.modules.attention. (#482)
Tested on 8GB eGPU nvidia setup so YMMV.
512x512 output, max VRAM stays same.
commit aba94b85e8
Author: Niek van der Maas <mail@niekvandermaas.nl>
Date: Fri Sep 9 15:01:37 2022 +0200
Fix macOS `pyenv` instructions, add code block highlight (#441)
Fix: `anaconda3-latest` does not work, specify the correct virtualenv, add missing init.
commit aac5102cf3
Author: Henry van Megen <h.vanmegen@gmail.com>
Date: Thu Sep 8 05:16:35 2022 +0200
Disabled debug output (#436)
Co-authored-by: Henry van Megen <hvanmegen@gmail.com>
commit 0ab5a36464
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 17:19:46 2022 -0400
fix missing lines in outputs
commit 5e433728b5
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 16:20:14 2022 -0400
upped max_steps in v1-finetune.yaml and fixed TI docs to address #493
commit 7708f4fb98
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 16:03:37 2022 -0400
slight efficiency gain by using += in attention.py
commit b86a1deb00
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Mon Sep 12 07:47:12 2022 +1200
Remove print statement styling (#504)
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
commit 4951e66103
Author: chromaticist <mhostick@gmail.com>
Date: Sun Sep 11 12:44:26 2022 -0700
Adding support for .bin files from huggingface concepts (#498)
* Adding support for .bin files from huggingface concepts
* Updating documentation to include huggingface .bin info
commit 79b445b0ca
Merge: a323070 f7662c1
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 15:39:38 2022 -0400
Merge branch 'development' of github.com:lstein/stable-diffusion into development
commit a323070a4d
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 15:28:57 2022 -0400
update requirements for new location of gfpgan
commit f7662c1808
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 15:00:24 2022 -0400
update requirements for changed location of gfpgan
commit 93c242c9fb
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 14:47:58 2022 -0400
make gfpgan_model_exists flag available to web interface
commit c7c6cd7735
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 14:43:07 2022 -0400
Update UPSCALE.md
New instructions needed to accommodate fact that the ESRGAN and GFPGAN packages are now installed by environment.yaml.
commit 77ca83e103
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 14:31:56 2022 -0400
Update CLI.md
Final documentation tweak.
commit 0ea145d188
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 14:29:26 2022 -0400
Update CLI.md
More doc fixes.
commit 162285ae86
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 14:28:45 2022 -0400
Update CLI.md
Minor documentation fix
commit 37c921dfe2
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 14:26:41 2022 -0400
documentation enhancements
commit 4f72cb44ad
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 13:05:38 2022 -0400
moved the notebook files into their own directory
commit 878ef2e9e0
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 12:58:06 2022 -0400
documentation tweaks
commit 4923118610
Merge: 16f6a67defafc0
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 12:51:25 2022 -0400
Merge branch 'development' of github.com:lstein/stable-diffusion into development
commit defafc0e8e
Author: Dominic Letz <dominic@diode.io>
Date: Sun Sep 11 18:51:01 2022 +0200
Enable upscaling on m1 (#474)
commit 16f6a6731d
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 12:47:26 2022 -0400
install GFPGAN inside SD repository in order to fix 'dark cast' issue #169
commit 0881d429f2
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Mon Sep 12 03:52:43 2022 +1200
Docs Update (#466)
Authored-by: @blessedcoolant
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
commit 9a29d442b4
Author: Gérald LONLAS <gerald@lonlas.com>
Date: Sun Sep 11 23:23:18 2022 +0800
Revert "Add 3x Upscale option on the Web UI (#442)" (#488)
This reverts commit f8a540881c.
commit d301836fbd
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 10:52:19 2022 -0400
can select prior output for init_img using -1, -2, etc
commit 70aa674e9e
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 10:34:06 2022 -0400
merge PR #495 - keep using float16 in ldm.modules.attention
commit 8748370f44
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 10:22:32 2022 -0400
negative -S indexing recovers correct previous seed; closes issue #476
commit 839e30e4b8
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 11 10:02:44 2022 -0400
improve CUDA VRAM monitoring
extra check that device==cuda before getting VRAM stats
commit bfb2781279
Author: tildebyte <337875+tildebyte@users.noreply.github.com>
Date: Sat Sep 10 10:15:56 2022 -0400
fix(readme): add note about updating env via conda (#475)
commit 5c43988862
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 10 10:02:43 2022 -0400
reduce VRAM memory usage by half during model loading
* This moves the call to half() before model.to(device) to avoid GPU
copy of full model. Improves speed and reduces memory usage dramatically
* This fix contributed by @mh-dm (Mihai)
commit 99122708ca
Merge: 817c4a2ecc6b75
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 10 09:54:34 2022 -0400
Merge branch 'development' of github.com:lstein/stable-diffusion into development
commit 817c4a26de
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 10 09:53:27 2022 -0400
remove -F option from normalized prompt; closes#483
commit ecc6b75a3e
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 10 09:53:27 2022 -0400
remove -F option from normalized prompt
commit 723d074442
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Sep 9 18:49:51 2022 -0400
Allow ctrl c when using --from_file (#472)
* added ansi escapes to highlight key parts of CLI session
* adjust exception handling so that ^C will abort when reading prompts from a file
commit 75f633cda8
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Sep 9 12:03:45 2022 -0400
re-add new logo
commit 10db192cc4
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Fri Sep 9 09:26:10 2022 -0400
changes to dogettx optimizations to run on m1
* Author @any-winter-4079
* Author @dogettx
Thanks to many individuals who contributed time and hardware to
benchmarking and debugging these changes.
commit c85ae00b33
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 23:57:45 2022 -0400
fix bug which caused seed to get "stuck" on previous image even when UI specified -1
commit 1b5aae3ef3
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 22:36:47 2022 -0400
add icon to dream web server
commit 6abf739315
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 22:25:09 2022 -0400
add favicon to web server
commit db825b8138
Merge: 33874baafee7f9
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 22:17:37 2022 -0400
Merge branch 'deNULL-development' into development
commit 33874bae8d
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 22:16:29 2022 -0400
Squashed commit of the following:
commit afee7f9cea
Merge: 6531446171f8db
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 22:14:32 2022 -0400
Merge branch 'development' of github.com:deNULL/stable-diffusion into deNULL-development
commit 171f8db742
Author: Denis Olshin <me@denull.ru>
Date: Thu Sep 8 03:15:20 2022 +0300
saving full prompt to metadata when using web ui
commit d7e67b62f0
Author: Denis Olshin <me@denull.ru>
Date: Thu Sep 8 01:51:47 2022 +0300
better logic for clicking to make variations
commit afee7f9cea
Merge: 6531446171f8db
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 22:14:32 2022 -0400
Merge branch 'development' of github.com:deNULL/stable-diffusion into deNULL-development
commit 653144694f
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 20:41:37 2022 -0400
work around unexplained crash when timesteps=1000 (#440)
* work around unexplained crash when timesteps=1000
* this fix seems to work
commit c33a84cdfd
Author: blessedcoolant <54517381+blessedcoolant@users.noreply.github.com>
Date: Fri Sep 9 12:39:51 2022 +1200
Add New Logo (#454)
* Add instructions on how to install alongside pyenv (#393)
Like probably many others, I have a lot of different virtualenvs, one for each project. Most of them are handled by `pyenv`.
After installing according to these instructions I had issues with ´pyenv`and `miniconda` fighting over the $PATH of my system.
But then I stumbled upon this nice solution on SO: https://stackoverflow.com/a/73139031 , upon which I have based my suggested changes.
It runs perfectly on my M1 setup, with the anaconda setup as a virtual environment handled by pyenv.
Feel free to incorporate these instructions as you see fit.
Thanks a million for all your hard work.
* Disabled debug output (#436)
Co-authored-by: Henry van Megen <hvanmegen@gmail.com>
* Add New Logo
Co-authored-by: Håvard Gulldahl <havard@lurtgjort.no>
Co-authored-by: Henry van Megen <h.vanmegen@gmail.com>
Co-authored-by: Henry van Megen <hvanmegen@gmail.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
commit f8a540881c
Author: Gérald LONLAS <gerald@lonlas.com>
Date: Fri Sep 9 01:45:54 2022 +0800
Add 3x Upscale option on the Web UI (#442)
commit 244239e5f6
Author: James Reynolds <magnusviri@users.noreply.github.com>
Date: Thu Sep 8 05:36:33 2022 -0600
macOS CI workflow, dream.py exits with an error, but the workflow com… (#396)
* macOS CI workflow, dream.py exits with an error, but the workflow completes.
* Files for testing
Co-authored-by: James Reynolds <magnsuviri@me.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
commit 711d49ed30
Author: James Reynolds <magnusviri@users.noreply.github.com>
Date: Thu Sep 8 05:35:08 2022 -0600
Cache model workflow (#394)
* Add workflow that caches the model, step 1 for CI
* Change name of workflow job
Co-authored-by: James Reynolds <magnsuviri@me.com>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
commit 7996a30e3a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Thu Sep 8 07:34:03 2022 -0400
add auto-creation of mask for inpainting (#438)
* now use a single init image for both image and mask
* turn on debugging for now to write out mask and image
* add back -M option as a fallback
commit a69ca31f34
Author: elliotsayes <elliotsayes@gmail.com>
Date: Thu Sep 8 15:30:06 2022 +1200
.gitignore WebUI temp files (#430)
* Add instructions on how to install alongside pyenv (#393)
Like probably many others, I have a lot of different virtualenvs, one for each project. Most of them are handled by `pyenv`.
After installing according to these instructions I had issues with ´pyenv`and `miniconda` fighting over the $PATH of my system.
But then I stumbled upon this nice solution on SO: https://stackoverflow.com/a/73139031 , upon which I have based my suggested changes.
It runs perfectly on my M1 setup, with the anaconda setup as a virtual environment handled by pyenv.
Feel free to incorporate these instructions as you see fit.
Thanks a million for all your hard work.
* .gitignore WebUI temp files
Co-authored-by: Håvard Gulldahl <havard@lurtgjort.no>
commit 5c6b612a72
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Sep 7 22:50:55 2022 -0400
fix bug that caused same seed to be redisplayed repeatedly
commit 56f155c590
Author: Johan Roxendal <johan@roxendal.com>
Date: Thu Sep 8 04:50:06 2022 +0200
added support for parsing run log and displaying images in the frontend init state (#410)
Co-authored-by: Johan Roxendal <johan.roxendal@litteraturbanken.se>
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
commit 41687746be
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Sep 7 20:24:35 2022 -0400
added missing initialization of latent_noise to None
commit 171f8db742
Author: Denis Olshin <me@denull.ru>
Date: Thu Sep 8 03:15:20 2022 +0300
saving full prompt to metadata when using web ui
commit d7e67b62f0
Author: Denis Olshin <me@denull.ru>
Date: Thu Sep 8 01:51:47 2022 +0300
better logic for clicking to make variations
commit d1d044aa87
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Sep 7 17:56:59 2022 -0400
actual image seed now written into web log rather than -1 (#428)
commit edada042b3
Author: Arturo Mendivil <60411196+artmen1516@users.noreply.github.com>
Date: Wed Sep 7 10:42:26 2022 -0700
Improve notebook and add requirements file (#422)
commit 29ab3c2028
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Sep 7 13:28:11 2022 -0400
disable neonpixel optimizations on M1 hardware (#414)
* disable neonpixel optimizations on M1 hardware
* fix typo that was causing random noise images on m1
commit 7670ecc63f
Author: cody <cnmizell@gmail.com>
Date: Wed Sep 7 12:24:41 2022 -0500
add more keyboard support on the web server (#391)
add ability to submit prompts with the "enter" key
add ability to cancel generations with the "escape" key
commit dd2aedacaf
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Wed Sep 7 13:23:53 2022 -0400
report VRAM usage stats during initial model loading (#419)
commit f6284777e6
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Tue Sep 6 17:12:39 2022 -0400
Squashed commit of the following:
commit 7d1344282d942a33dcecda4d5144fc154ec82915
Merge: caf4ea3ebeb556
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 5 10:07:27 2022 -0400
Merge branch 'development' of github.com:WebDev9000/stable-diffusion into WebDev9000-development
commit ebeb556af9
Author: Web Dev 9000 <rirath@gmail.com>
Date: Sun Sep 4 18:05:15 2022 -0700
Fixed unintentionally removed lines
commit ff2c4b9a1b
Author: Web Dev 9000 <rirath@gmail.com>
Date: Sun Sep 4 17:50:13 2022 -0700
Add ability to recreate variations via image click
commit c012929cda
Author: Web Dev 9000 <rirath@gmail.com>
Date: Sun Sep 4 14:35:33 2022 -0700
Add files via upload
commit 02a6018992
Author: Web Dev 9000 <rirath@gmail.com>
Date: Sun Sep 4 14:35:07 2022 -0700
Add files via upload
commit eef788981c
Author: Olivier Louvignes <olivier@mg-crea.com>
Date: Tue Sep 6 12:41:08 2022 +0200
feat(txt2img): allow from_file to work with len(lines) < batch_size (#349)
commit 720e5cd651
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 5 20:40:10 2022 -0400
Refactoring simplet2i (#387)
* start refactoring -not yet functional
* first phase of refactor done - not sure weighted prompts working
* Second phase of refactoring. Everything mostly working.
* The refactoring has moved all the hard-core inference work into
ldm.dream.generator.*, where there are submodules for txt2img and
img2img. inpaint will go in there as well.
* Some additional refactoring will be done soon, but relatively
minor work.
* fix -save_orig flag to actually work
* add @neonsecret attention.py memory optimization
* remove unneeded imports
* move token logging into conditioning.py
* add placeholder version of inpaint; porting in progress
* fix crash in img2img
* inpainting working; not tested on variations
* fix crashes in img2img
* ported attention.py memory optimization #117 from basujindal branch
* added @torch_no_grad() decorators to img2img, txt2img, inpaint closures
* Final commit prior to PR against development
* fixup crash when generating intermediate images in web UI
* rename ldm.simplet2i to ldm.generate
* add backward-compatibility simplet2i shell with deprecation warning
* add back in mps exception, addresses @vargol comment in #354
* replaced Conditioning class with exported functions
* fix wrong type of with_variations attribute during intialization
* changed "image_iterator()" to "get_make_image()"
* raise NotImplementedError for calling get_make_image() in parent class
* Update ldm/generate.py
better error message
Co-authored-by: Kevin Gibbons <bakkot@gmail.com>
* minor stylistic fixes and assertion checks from code review
* moved get_noise() method into img2img class
* break get_noise() into two methods, one for txt2img and the other for img2img
* inpainting works on non-square images now
* make get_noise() an abstract method in base class
* much improved inpainting
Co-authored-by: Kevin Gibbons <bakkot@gmail.com>
commit 1ad2a8e567
Author: thealanle <35761977+thealanle@users.noreply.github.com>
Date: Mon Sep 5 17:35:04 2022 -0700
Fix --outdir function for web (#373)
* Fix --outdir function for web
* Removed unnecessary hardcoded path
commit 52d8bb2836
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 5 10:31:59 2022 -0400
Squashed commit of the following:
commit 0cd48e932f1326e000c46f4140f98697eb9bdc79
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Mon Sep 5 10:27:43 2022 -0400
resolve conflicts with development
commit d7bc8c12e0
Author: Scott McMillin <scott@scottmcmillin.com>
Date: Sun Sep 4 18:52:09 2022 -0500
Add title attribute back to img tag
commit 5397c89184
Author: Scott McMillin <scott@scottmcmillin.com>
Date: Sun Sep 4 13:49:46 2022 -0500
Remove temp code
commit 1da080b509
Author: Scott McMillin <scott@scottmcmillin.com>
Date: Sun Sep 4 13:33:56 2022 -0500
Cleaned up HTML; small style changes; image click opens image; add seed to figcaption beneath image
commit caf4ea3d89
Author: Adam Rice <adam@askadam.io>
Date: Mon Sep 5 10:05:39 2022 -0400
Add a 'Remove Image' button to clear the file upload field (#382)
* added "remove image" button
* styled a new "remove image" button
* Update index.js
commit 95c088b303
Author: Kevin Gibbons <bakkot@gmail.com>
Date: Sun Sep 4 19:04:14 2022 -0700
Revert "Add CORS headers to dream server to ease integration with third-party web interfaces" (#371)
This reverts commit 91e826e5f4.
commit a20113d5a3
Author: Kevin Gibbons <bakkot@gmail.com>
Date: Sun Sep 4 18:59:12 2022 -0700
put no_grad decorator on make_image closures (#375)
commit 0f93dadd6a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 4 21:39:15 2022 -0400
fix several dangling references to --gfpgan option, which no longer exists
commit f4004f660e
Author: tildebyte <337875+tildebyte@users.noreply.github.com>
Date: Sun Sep 4 19:43:04 2022 -0400
TOIL(requirements): Split requirements to per-platform (#355)
* toil(reqs): split requirements to per-platform
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* toil(reqs): fix for Win and Lin...
...allow pip to resolve latest torch, numpy
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
* toil(install): update reqs in Win install notebook
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
Signed-off-by: Ben Alkov <ben.alkov@gmail.com>
commit 4406fd138d
Merge: 5116c81fd7a72e
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 4 08:23:53 2022 -0400
Merge branch 'SebastianAigner-main' into development
Add support for full CORS headers for dream server.
commit fd7a72e147
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 4 08:23:11 2022 -0400
remove debugging message
commit 3a2be621f3
Merge: 91e826e5116c81
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sun Sep 4 08:15:51 2022 -0400
Merge branch 'development' into main
commit 5116c8178c
Author: Justin Wong <1584142+wongjustin99@users.noreply.github.com>
Date: Sun Sep 4 07:17:58 2022 -0400
fix save_original flag saving to the same filename (#360)
* Update README.md with new Anaconda install steps (#347)
pip3 version did not work for me and this is the recommended way to install Anaconda now it seems
* fix save_original flag saving to the same filename
Before this, the `--save_orig` flag was not working. The upscaled/GFPGAN would overwrite the original output image.
Co-authored-by: greentext2 <112735219+greentext2@users.noreply.github.com>
commit 91e826e5f4
Author: Sebastian Aigner <SebastianAigner@users.noreply.github.com>
Date: Sun Sep 4 10:22:54 2022 +0200
Add CORS headers to dream server to ease integration with third-party web interfaces
commit 6266d9e8d6
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 15:45:20 2022 -0400
remove stray debugging message
commit 138956e516
Author: greentext2 <112735219+greentext2@users.noreply.github.com>
Date: Sat Sep 3 13:38:57 2022 -0500
Update README.md with new Anaconda install steps (#347)
pip3 version did not work for me and this is the recommended way to install Anaconda now it seems
commit 60be735e80
Author: Cora Johnson-Roberson <cora.johnson.roberson@gmail.com>
Date: Sat Sep 3 14:28:34 2022 -0400
Switch to regular pytorch channel and restore Python 3.10 for Macs. (#301)
* Switch to regular pytorch channel and restore Python 3.10 for Macs.
Although pytorch-nightly should in theory be faster, it is currently
causing increased memory usage and slower iterations:
https://github.com/lstein/stable-diffusion/pull/283#issuecomment-1234784885
This changes the environment-mac.yaml file back to the regular pytorch
channel and moves the `transformers` dep into pip for now (since it
cannot be satisfied until tokenizers>=0.11 is built for Python 3.10).
* Specify versions for Pip packages as well.
commit d0d95d3a2a
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 14:10:31 2022 -0400
make initimg appear in web log
commit b90a215000
Merge: 1eee8116270e31
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 13:47:15 2022 -0400
Merge branch 'prixt-seamless' into development
commit 6270e313b8
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 13:46:29 2022 -0400
add credit to prixt for seamless circular tiling
commit a01b7bdc40
Merge: 1eee8119d88abe
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 13:43:04 2022 -0400
add web interface for seamless option
commit 1eee8111b9
Merge: 64eca42fb857f0
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 12:33:39 2022 -0400
Merge branch 'development' of github.com:lstein/stable-diffusion into development
commit 64eca42610
Merge: 9130ad721a1f68
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 12:33:05 2022 -0400
Merge branch 'main' into development
* brings in small documentation fixes that were
added directly to main during release tweaking.
commit fb857f05ba
Author: Lincoln Stein <lincoln.stein@gmail.com>
Date: Sat Sep 3 12:07:07 2022 -0400
fix typo in docs
commit 9d88abe2ea
Author: prixt <paraxite@naver.com>
Date: Sat Sep 3 22:42:16 2022 +0900
fixed typo
commit a61e49bc97
Author: prixt <paraxite@naver.com>
Date: Sat Sep 3 22:39:35 2022 +0900
* Removed unnecessary code
* Added description about --seamless
commit 02bee4fdb1
Author: prixt <paraxite@naver.com>
Date: Sat Sep 3 16:08:03 2022 +0900
added --seamless tag logging to normalize_prompt
commit d922b53c26
Author: prixt <paraxite@naver.com>
Date: Sat Sep 3 15:13:31 2022 +0900
added seamless tiling mode and commands
* This moves the call to half() before model.to(device) to avoid GPU
copy of full model. Improves speed and reduces memory usage dramatically
* This fix contributed by @mh-dm (Mihai)
Like probably many others, I have a lot of different virtualenvs, one for each project. Most of them are handled by `pyenv`.
After installing according to these instructions I had issues with ´pyenv`and `miniconda` fighting over the $PATH of my system.
But then I stumbled upon this nice solution on SO: https://stackoverflow.com/a/73139031 , upon which I have based my suggested changes.
It runs perfectly on my M1 setup, with the anaconda setup as a virtual environment handled by pyenv.
Feel free to incorporate these instructions as you see fit.
Thanks a million for all your hard work.
Thanks for taking the time to fill out this Bug Report!
- type:checkboxes
attributes:
label:Is there an existing issue for this?
description:|
Please use the [search function](https://github.com/invoke-ai/InvokeAI/issues?q=is%3Aissue+is%3Aopen+label%3Abug)
irst to see if an issue already exists for the bug you encountered.
options:
- label:I have searched the existing issues
required:true
- type:markdown
attributes:
value:__Describe your environment__
- type:dropdown
id:os_dropdown
attributes:
label:OS
description:Which operating System did you use when the bug occured
multiple:false
options:
- 'Linux'
- 'Windows'
- 'macOS'
validations:
required:true
- type:dropdown
id:gpu_dropdown
attributes:
label:GPU
description:Which kind of Graphic-Adapter is your System using
multiple:false
options:
- 'cuda'
- 'amd'
- 'mps'
- 'cpu'
validations:
required:true
- type:input
id:vram
attributes:
label:VRAM
description:Size of the VRAM if known
placeholder:8GB
validations:
required:false
- type:input
id:version-number
attributes:
label:What version did you experience this issue on?
description:|
Please share the version of Invoke AI that you experienced the issue on. If this is not the latest version, please update first to confirm the issue still exists. If you are testing main, please include the commit hash instead.
placeholder:X.X.X
validations:
required:true
- type:textarea
id:what-happened
attributes:
label:What happened?
description:|
Briefly describe what happened, what you expected to happen and how to reproduce this bug.
placeholder:When using the webinterface and right-clicking on button X instead of the popup-menu there error Y appears
validations:
required:true
- type:textarea
attributes:
label:Screenshots
description:If applicable, add screenshots to help explain your problem
placeholder:this is what the result looked like <screenshot>
validations:
required:false
- type:textarea
attributes:
label:Additional context
description:Add any other context about the problem here
placeholder:Only happens when there is full moon and Friday the 13th on Christmas Eve 🎅🏻
validations:
required:false
- type:input
id:contact
attributes:
label:Contact Details
description:__OPTIONAL__ How can we get in touch with you if we need more info (besides this issue)?
stale-issue-message:"There has been no activity in this issue for ${{ env.DAYS_BEFORE_ISSUE_STALE }} days. If this issue is still being experienced, please reply with an updated confirmation that the issue is still being experienced with the latest release."
close-issue-message:"Due to inactivity, this issue was automatically closed. If you are still experiencing the issue, please recreate the issue."
- Supports a Google Colab notebook for a standalone server running on Google hardware [Arturo Mendivil](https://github.com/artmen1516)
- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling [Kevin Gibbons](https://github.com/bakkot)
- WebUI supports incremental display of in-progress images during generation [Kevin Gibbons](https://github.com/bakkot)
- Output directory can be specified on the dream> command line.
- The grid was displaying duplicated images when not enough images to fill the final row [Muhammad Usama](https://github.com/SMUsamaShah)
- Can specify --grid on dream.py command line as the default.
- Miscellaneous internal bug and stability fixes.
---
## v1.12 (28 August 2022)
- Improved file handling, including ability to read prompts from standard input.
(kudos to [Yunsaki](https://github.com/yunsaki)
- The web server is now integrated with the dream.py script. Invoke by adding --web to
the dream.py command arguments.
- Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically
enabled if the GFPGAN directory is located as a sibling to Stable Diffusion.
VRAM requirements are modestly reduced. Thanks to both [Blessedcoolant](https://github.com/blessedcoolant) and
[Oceanswave](https://github.com/oceanswave) for their work on this.
- You can now swap samplers on the dream> command line. [Blessedcoolant](https://github.com/blessedcoolant)
---
## v1.11 (26 August 2022)
- NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave)
- You now can specify a seed of -1 to use the previous image's seed, -2 to use the seed for the image generated before that, etc.
Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch.
- Variant generation support temporarily disabled pending more general solution.
- Created a feature branch named **yunsaki-morphing-dream** which adds experimental support for
iteratively modifying the prompt and its parameters. Please see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86)
for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified
significantly.
---
## v1.10 (25 August 2022)
- A barebones but fully functional interactive web server for online generation of txt2img and img2img.
---
## v1.09 (24 August 2022)
- A new -v option allows you to generate multiple variants of an initial image
in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [
See this discussion in the PR for examples and details on use](https://github.com/lstein/stable-diffusion/pull/71#issuecomment-1226700810))
- Added ability to personalize text to image generation (kudos to [Oceanswave](https://github.com/Oceanswave) and [nicolai256](https://github.com/nicolai256))
- Enabled all of the samplers from k_diffusion
---
## v1.08 (24 August 2022)
- Escape single quotes on the dream> command before trying to parse. This avoids
parse errors.
- Removed instruction to get Python3.8 as first step in Windows install.
Anaconda3 does it for you.
- Added bounds checks for numeric arguments that could cause crashes.
- Cleaned up the copyright and license agreement files.
---
## v1.07 (23 August 2022)
- Image filenames will now never fill gaps in the sequence, but will be assigned the
next higher name in the chosen directory. This ensures that the alphabetic and chronological
sort orders are the same.
---
## v1.06 (23 August 2022)
- Added weighted prompt support contributed by [xraxra](https://github.com/xraxra)
- Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais)
---
## v1.05 (22 August 2022 - after the drop)
- Filenames now use the following formats:
000010.95183149.png -- Two files produced by the same command (e.g. -n2),
000010.26742632.png -- distinguished by a different seed.
000011.455191342.01.png -- Two files produced by the same command using
000011.455191342.02.png -- a batch size>1 (e.g. -b2). They have the same seed.
000011.4160627868.grid#1-4.png -- a grid of four images (-g); the whole grid can
be regenerated with the indicated key
- It should no longer be possible for one image to overwrite another
- You can use the "cd" and "pwd" commands at the dream> prompt to set and retrieve
the path of the output directory.
---
## v1.04 (22 August 2022 - after the drop)
- Updated README to reflect installation of the released weights.
- Suppressed very noisy and inconsequential warning when loading the frozen CLIP
tokenizer.
---
## v1.03 (22 August 2022)
- The original txt2img and img2img scripts from the CompViz repository have been moved into
a subfolder named "orig_scripts", to reduce confusion.
---
## v1.02 (21 August 2022)
- A copy of the prompt and all of its switches and options is now stored in the corresponding
image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py,
or an image editor that allows you to explore the full metadata.
**Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!**
---
## v1.01 (21 August 2022)
- added k_lms sampling.
**Please run "conda env update -f environment.yaml" to load the k_lms dependencies!!**
- use half precision arithmetic by default, resulting in faster execution and lower memory requirements
Pass argument --full_precision to dream.py to get slower but more accurate image generation
Invoke-AI is a community of software developers, researchers, and user
interface experts who have come together on a voluntary basis to build
software tools which support cutting edge AI text-to-image
applications. This community is open to anyone who wishes to
contribute to the effort and has the skill and time to do so.
# Our Values
The InvokeAI team is a diverse community which includes individuals
from various parts of the world and many walks of life. Despite our
differences, we share a number of core values which we ask prospective
contributors to understand and respect. We believe:
1. That Open Source Software is a positive force in the world. We
create software that can be used, reused, and redistributed, without
restrictions, under a straightforward Open Source license (MIT). We
believe that Open Source benefits society as a whole by increasing the
availability of high quality software to all.
2. That those who create software should receive proper attribution
for their creative work. While we support the exchange and reuse of
Open Source Software, we feel strongly that the original authors of a
piece of code should receive credit for their contribution, and we
endeavor to do so whenever possible.
3. That there is moral ambiguity surrounding AI-assisted art. We are
aware of the moral and ethical issues surrounding the release of the
Stable Diffusion model and similar products. We are aware that, due to
the composition of their training sets, current AI-generated image
models are biased against certain ethnic groups, cultural concepts of
beauty, ethnic stereotypes, and gender roles.
1. We recognize the potential for harm to these groups that these biases
represent and trust that future AI models will take steps towards
reducing or eliminating the biases noted above, respect and give due
credit to the artists whose work is sourced, and call on developers
and users to favor these models over the older ones as they become
available.
4. We are deeply committed to ensuring that this technology benefits
everyone, including artists. We see AI art not as a replacement for
the artist, but rather as a tool to empower them. With that
in mind, we are constantly debating how to build systems that put
artists’ needs first: tools which can be readily integrated into an
artist’s existing workflows and practices, enhancing their work and
helping them to push it further. Every decision we take as a team,
which includes several artists, aims to build towards that goal.
5. That artificial intelligence can be a force for good in the world,
but must be used responsibly. Artificial intelligence technologies
have the potential to improve society, in everything from cancer care,
to customer service, to creative writing.
1. While we do not believe that software should arbitrarily limit what
users can do with it, we recognize that when used irresponsibly, AI
has the potential to do much harm. Our Discord server is actively
moderated in order to minimize the potential of harm from
user-contributed images. In addition, we ask users of our software to
refrain from using it in any way that would cause mental, emotional or
physical harm to individuals and vulnerable populations including (but
not limited to) women; minors; ethnic minorities; religious groups;
members of LGBTQIA communities; and people with disabilities or
impairments.
2. Note that some of the image generation AI models which the Invoke-AI
toolkit supports carry licensing agreements which impose restrictions
on how the model is used. We ask that our users read and agree to
these terms if they wish to make use of these models. These agreements
are distinct from the MIT license which applies to the InvokeAI
software and source code.
6. That mutual respect is key to a healthy software development
community. Members of the InvokeAI community are expected to treat
each other with respect, beneficence, and empathy. Each of us has a
different background and a unique set of skills. We strive to help
each other grow and gain new skills, and we apportion expectations in
a way that balances the members' time, skillset, and interest
area. Disputes are resolved by open and honest communication.
## Signature
This document has been collectively crafted and approved by the current InvokeAI team members, as of 28 Nov 2022: **lstein** (Lincoln Stein), **blessedcoolant**, **hipsterusername** (Kent Keirsey), **Kyle0654** (Kyle Schouviller), **damian0815**, **mauwii** (Matthias Wild), **Netsvetaev** (Artur Netsvetaev), **psychedelicious**, **tildebyte**, **keturn**, and **ebr** (Eugene Brodsky). Although individuals within the group may hold differing views on particular details and/or their implications, we are all in agreement about its fundamental statements, as well as their significance and importance to this project moving forward.
*Stable Diffusion was made possible thanks to a collaboration with [Stability AI](https://stability.ai/) and [Runway](https://runwayml.com/) and builds upon our previous work:*
[**High-Resolution Image Synthesis with Latent Diffusion Models**](https://ommer-lab.com/research/latent-diffusion-models/)<br/>
which is available on [GitHub](https://github.com/CompVis/latent-diffusion). PDF at [arXiv](https://arxiv.org/abs/2112.10752). Please also visit our [Project page](https://ommer-lab.com/research/latent-diffusion-models/).
[Stable Diffusion](#stable-diffusion-v1) is a latent text-to-image diffusion
model.
Thanks to a generous compute donation from [Stability AI](https://stability.ai/) and support from [LAION](https://laion.ai/), we were able to train a Latent Diffusion Model on 512x512 images from a subset of the [LAION-5B](https://laion.ai/blog/laion-5b/) database.
Similar to Google's [Imagen](https://arxiv.org/abs/2205.11487),
this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts.
With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 10GB VRAM.
See [this section](#stable-diffusion-v1) below and the [model card](https://huggingface.co/CompVis/stable-diffusion).
## Requirements
A suitable [conda](https://conda.io/) environment named `ldm` can be created
and activated with:
```
conda env create -f environment.yaml
conda activate ldm
```
You can also update an existing [latent diffusion](https://github.com/CompVis/latent-diffusion) environment by running
```
conda install pytorch torchvision -c pytorch
pip install transformers==4.19.2
pip install -e .
```
## Stable Diffusion v1
Stable Diffusion v1 refers to a specific configuration of the model
architecture that uses a downsampling-factor 8 autoencoder with an 860M UNet
and CLIP ViT-L/14 text encoder for the diffusion model. The model was pretrained on 256x256 images and
then finetuned on 512x512 images.
*Note: Stable Diffusion v1 is a general text-to-image diffusion model and therefore mirrors biases and (mis-)conceptions that are present
in its training data.
Details on the training procedure and data, as well as the intended use of the model can be found in the corresponding [model card](https://huggingface.co/CompVis/stable-diffusion).
Research into the safe deployment of general text-to-image models is an ongoing effort. To prevent misuse and harm, we currently provide access to the checkpoints only for [academic research purposes upon request](https://stability.ai/academia-access-form).
**This is an experiment in safe and community-driven publication of a capable and general text-to-image model. We are working on a public release with a more permissive license that also incorporates ethical considerations.***
[Request access to Stable Diffusion v1 checkpoints for academic research](https://stability.ai/academia-access-form)
### Weights
We currently provide three checkpoints, `sd-v1-1.ckpt`, `sd-v1-2.ckpt` and `sd-v1-3.ckpt`,
which were trained as follows,
-`sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
-`sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`.
515k steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en,
filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
-`sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-improved-aesthetics" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
steps show the relative improvements of the checkpoints:
python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms
```
By default, this uses a guidance scale of `--scale 7.5`, [Katherine Crowson's implementation](https://github.com/CompVis/latent-diffusion/pull/51) of the [PLMS](https://arxiv.org/abs/2202.09778) sampler,
and renders images of size 512x512 (which it was trained on) in 50 steps. All supported arguments are listed below (type `python scripts/txt2img.py --help`).
--config CONFIG path to config which constructs model
--ckpt CKPT path to checkpoint of model
--seed SEED the seed (for reproducible sampling)
--precision {full,autocast}
evaluate at this precision
```
Note: The inference config for all v1 versions is designed to be used with EMA-only checkpoints.
For this reason `use_ema=False` is set in the configuration, otherwise the code will try to switch from
non-EMA to EMA weights. If you want to examine the effect of EMA vs no EMA, we provide "full" checkpoints
which contain both types of weights. For these, `use_ema=False` will load and use the non-EMA weights.
#### Diffusers Integration
Another way to download and sample Stable Diffusion is by using the [diffusers library](https://github.com/huggingface/diffusers/tree/main#new--stable-diffusion-is-now-fully-compatible-with-diffusers)
```py
# make sure you're logged in with `huggingface-cli login`
prompt="a photo of an astronaut riding a horse on mars"
withautocast("cuda"):
image=pipe(prompt)["sample"][0]
image.save("astronaut_rides_horse.png")
```
### Image Modification with Stable Diffusion
By using a diffusion-denoising mechanism as first proposed by [SDEdit](https://arxiv.org/abs/2108.01073), the model can be used for different
tasks such as text-guided image-to-image translation and upscaling. Similar to the txt2img sampling script,
we provide a script to perform image modification with Stable Diffusion.
The following describes an example where a rough sketch made in [Pinta](https://www.pinta-project.com/) is converted into a detailed artwork.
```
python scripts/img2img.py --prompt "A fantasy landscape, trending on artstation" --init-img <path-to-img.jpg> --strength 0.8
```
Here, strength is a value between 0.0 and 1.0, that controls the amount of noise that is added to the input image.
Values that approach 1.0 allow for lots of variations but will also produce images that are not semantically consistent with the input. See the following example.
This procedure can, for example, also be used to upscale samples from the base model.
## Comments
- Our codebase for the diffusion models builds heavily on [OpenAI's ADM codebase](https://github.com/openai/guided-diffusion)
and [https://github.com/lucidrains/denoising-diffusion-pytorch](https://github.com/lucidrains/denoising-diffusion-pytorch).
Thanks for open-sourcing!
- The implementation of the transformer encoder is from [x-transformers](https://github.com/lucidrains/x-transformers) by [lucidrains](https://github.com/lucidrains?tab=repositories).
## BibTeX
```
@misc{rombach2021highresolution,
title={High-Resolution Image Synthesis with Latent Diffusion Models},
author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
*I haven't tested any of this on Intel Macs but I have read that one person got
it to work, so Apple Silicon might not be requried.
Things have moved really fast and so these instructions change often and are
often out-of-date. One of the problems is that there are so many different ways to
run this.
We are trying to build a testing setup so that when we make changes it doesn't
always break.
How to (this hasn't been 100% tested yet):
First get the weights checkpoint download started - it's big:
1. Sign up at https://huggingface.co
2. Go to the [Stable diffusion diffusion model page](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)
3. Accept the terms and click Access Repository:
4. Download [sd-v1-4.ckpt (4.27 GB)](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/blob/main/sd-v1-4.ckpt) and note where you have saved it (probably the Downloads folder)
While that is downloading, open Terminal and run the following commands one at a time.
If `conda env create -f environment-mac.yaml` takes forever run this.
git clean -f
And run this.
conda clean --yes --all
Or you could reset Anaconda.
conda update --force-reinstall -y -n base -c defaults conda
### "No module named cv2", torch, 'ldm', 'transformers', 'taming', etc.
There are several causes of these errors.
First, did you remember to `conda activate ldm`? If your terminal prompt
begins with "(ldm)" then you activated it. If it begins with "(base)"
or something else you haven't.
Second, you might've run `./scripts/preload_models.py` or `./scripts/dream.py`
instead of `python ./scripts/preload_models.py` or `python ./scripts/dream.py`.
The cause of this error is long so it's below.
Third, if it says you're missing taming you need to rebuild your virtual
environment.
conda env remove -n ldm
conda env create -f environment-mac.yaml
Fourth, If you have activated the ldm virtual environment and tried rebuilding
it, maybe the problem could be that I have something installed that
you don't and you'll just need to manually install it. Make sure you
activate the virtual environment so it installs there instead of
globally.
conda activate ldm
pip install *name*
You might also need to install Rust (I mention this again below).
### How many snakes are living in your computer?
Here's the reason why you have to specify which python to use.
There are several versions of python on macOS and the computer is
picking the wrong one. More specifically, preload_models.py and dream.py says to
find the first `python3` in the path environment variable. You can see which one
it is picking with `which python3`. These are the mostly likely paths you'll see.
% which python3
/usr/bin/python3
The above path is part of the OS. However, that path is a stub that asks you if
you want to install Xcode. If you have Xcode installed already,
/usr/bin/python3 will execute /Library/Developer/CommandLineTools/usr/bin/python3 or
/Applications/Xcode.app/Contents/Developer/usr/bin/python3 (depending on which
Xcode you've selected with `xcode-select`).
% which python3
/opt/homebrew/bin/python3
If you installed python3 with Homebrew and you've modified your path to search
for Homebrew binaries before system ones, you'll see the above path.
% which python
/opt/anaconda3/bin/python
If you drop the "3" you get an entirely different python. Note: starting in
macOS 12.3, /usr/bin/python no longer exists (it was python 2 anyway).
If you have Anaconda installed, this is what you'll see. There is a
/opt/anaconda3/bin/python3 also.
(ldm) % which python
/Users/name/miniforge3/envs/ldm/bin/python
This is what you'll see if you have miniforge and you've correctly activated
the ldm environment. This is the goal.
It's all a mess and you should know [how to modify the path environment variable](https://support.apple.com/guide/terminal/use-environment-variables-apd382cc5fa-4f58-4449-b20a-41c53c006f8f/mac)
if you want to fix it. Here's a brief hint of all the ways you can modify it
(don't really have the time to explain it all here).
- ~/.zshrc
- ~/.bash_profile
- ~/.bashrc
- /etc/paths.d
- /etc/path
Which one you use will depend on what you have installed except putting a file
in /etc/paths.d is what I prefer to do.
### Debugging?
Tired of waiting for your renders to finish before you can see if it
works? Reduce the steps! The image quality will be horrible but at least you'll
### OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'...
python scripts/preload_models.py
### "The operator [name] is not current implemented for the MPS device." (sic)
Example error.
```
...
NotImplementedError: The operator 'aten::_index_put_impl_' is not current implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on [https://github.com/pytorch/pytorch/issues/77764](https://github.com/pytorch/pytorch/issues/77764). As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.
```
The lstein branch includes this fix in [environment-mac.yaml](https://github.com/lstein/stable-diffusion/blob/main/environment-mac.yaml).
### "Could not build wheels for tokenizers"
I have not seen this error because I had Rust installed on my computer before I started playing with Stable Diffusion. The fix is to install Rust.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
### How come `--seed` doesn't work?
First this:
> Completely reproducible results are not guaranteed across PyTorch
releases, individual commits, or different platforms. Furthermore,
results may not be reproducible between CPU and GPU executions, even
Second, we might have a fix that at least gets a consistent seed sort of. We're
still working on it.
### libiomp5.dylib error?
OMP: Error #15: Initializing libiomp5.dylib, but found libomp.dylib already initialized.
You are likely using an Intel package by mistake. Be sure to run conda with
the environment variable `CONDA_SUBDIR=osx-arm64`, like so:
`CONDA_SUBDIR=osx-arm64 conda install ...`
This error happens with Anaconda on Macs when the Intel-only `mkl` is pulled in by
a dependency. [nomkl](https://stackoverflow.com/questions/66224879/what-is-the-nomkl-python-package-used-for)
is a metapackage designed to prevent this, by making it impossible to install
`mkl`, but if your environment is already broken it may not work.
Do *not* use `os.environ['KMP_DUPLICATE_LIB_OK']='True'` or equivalents as this
masks the underlying issue of using Intel packages.
### Not enough memory.
This seems to be a common problem and is probably the underlying
problem for a lot of symptoms (listed below). The fix is to lower your
image size or to add `model.half()` right after the model is loaded. I
should probably test it out. I've read that the reason this fixes
problems is because it converts the model from 32-bit to 16-bit and
that leaves more RAM for other things. I have no idea how that would
affect the quality of the images though.
See [this issue](https://github.com/CompVis/stable-diffusion/issues/71).
### "Error: product of dimension sizes > 2**31'"
This error happens with img2img, which I haven't played with too much
yet. But I know it's because your image is too big or the resolution
isn't a multiple of 32x32. Because the stable-diffusion model was
trained on images that were 512 x 512, it's always best to use that
output size (which is the default). However, if you're using that size
and you get the above error, try 256 x 256 or 512 x 256 or something
as the source image.
BTW, 2**31-1 = [2,147,483,647](https://en.wikipedia.org/wiki/2,147,483,647#In_computing), which is also 32-bit signed [LONG_MAX](https://en.wikipedia.org/wiki/C_data_types) in C.
### I just got Rickrolled! Do I have a virus?
You don't have a virus. It's part of the project. Here's
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
```
Update to the latest version of lstein/stable-diffusion. We were
patching pytorch but we found a file in stable-diffusion that we could
change instead. This is a 32-bit vs 16-bit problem.
### The processor must support the Intel bla bla bla
What? Intel? On an Apple Silicon?
Intel MKL FATAL ERROR: This system does not meet the minimum requirements for use of the Intel(R) Math Kernel Library.
The processor must support the Intel(R) Supplemental Streaming SIMD Extensions 3 (Intel(R) SSSE3) instructions.
The processor must support the Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) instructions.
The processor must support the Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
This is due to the Intel `mkl` package getting picked up when you try to install
something that depends on it-- Rosetta can translate some Intel instructions but
not the specialized ones here. To avoid this, make sure to use the environment
variable `CONDA_SUBDIR=osx-arm64`, which restricts the Conda environment to only
use ARM packages, and use `nomkl` as described above.
### input types 'tensor<2x1280xf32>' and 'tensor<*xf16>' are not broadcast compatible
May appear when just starting to generate, e.g.:
```
dream> clouds
Generating: 0%| | 0/1 [00:00<?, ?it/s]/Users/[...]/dev/stable-diffusion/ldm/modules/embedding_manager.py:152: UserWarning: The operator 'aten::nonzero' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/_temp/anaconda/conda-bld/pytorch_1662016319283/work/aten/src/ATen/mps/MPSFallback.mm:11.)
placeholder_idx = torch.where(
loc("mps_add"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/20d6c351-ee94-11ec-bcaf-7247572f23b4/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":219:0)): error: input types 'tensor<2x1280xf32>' and 'tensor<*xf16>' are not broadcast compatible
LLVM ERROR: Failed to infer result type(s).
Abort trap: 6
/Users/[...]/opt/anaconda3/envs/ldm/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
```
Macs do not support autocast/mixed-precision. Supply `--full_precision` to use float32 everywhere.
"are available in the wiki (you'll only need steps 1, 2, & 3 )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Run each cell in turn. In VSCode, either hit SHIFT-ENTER, or click on the little ▶️ to the left of the cell. In Jupyter/JupyterLab, you **must** hit SHIFT-ENTER"
"pew new --python 3.10 -r requirements.txt --dont-activate ldm"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Switch the notebook kernel to the new 'ldm' environment!\n",
"\n",
"## VSCode: restart VSCode and come back to this cell\n",
"\n",
"1. Ctrl+Shift+P\n",
"1. Type \"Select Interpreter\" and select \"Jupyter: Select Interpreter to Start Jupyter Server\"\n",
"1. VSCode will say that it needs to install packages. Click the \"Install\" button.\n",
"1. Once the install is finished, do 1 & 2 again\n",
"1. Pick 'ldm'\n",
"1. Run the following cell"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%cd stable-diffusion"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"## Jupyter/JupyterLab\n",
"\n",
"1. Run the cell below\n",
"1. Click on the toolbar where it says \"(ipyknel)\" ↗️. You should get a pop-up asking you to \"Select Kernel\". Pick 'ldm' from the drop-down.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### DO NOT RUN THE FOLLOWING CELL IF YOU ARE USING VSCODE!!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# DO NOT RUN THIS CELL IF YOU ARE USING VSCODE!!\n",
"%%cmd\n",
"pew workon ldm\n",
"pip3 install ipykernel\n",
"python -m ipykernel install --name=ldm"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### When running the next cell, Jupyter/JupyterLab users might get a warning saying \"IProgress not found\". This can be ignored."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%run \"scripts/preload_models.py\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%cmd\n",
"mkdir \"models/ldm/stable-diffusion-v1\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Now copy the SD model you downloaded from Hugging Face into the above new directory, and (if necessary) rename it to 'model.ckpt'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Now go create some magic!\n",
"\n",
"VSCode\n",
"\n",
"- The actual input box for the 'dream' prompt will appear at the very top of the VSCode window. Type in your commands and hit 'ENTER'.\n",
"- To quit, hit the 'Interrupt' button in the toolbar up there ⬆️ a couple of times, then hit ENTER (you'll probably see a terrifying traceback from Python - just ignore it).\n",
"\n",
"Jupyter/JupyterLab\n",
"\n",
"- The input box for the 'dream' prompt will appear below. Type in your commands and hit 'ENTER'.\n",
"- To quit, hit the interrupt button (⏹️) in the toolbar up there ⬆️ a couple of times, then hit ENTER (you'll probably see a terrifying traceback from Python - just ignore it)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%run \"scripts/dream.py\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Once this seems to be working well, you can try opening a terminal\n",
"\n",
"- VSCode: type ('CTRL+`')\n",
"- Jupyter/JupyterLab: File|New Terminal\n",
"- Or jump out of the notebook entirely, and open Powershell/Command Prompt\n",
"\n",
"Now:\n",
"\n",
"1. `cd` to wherever the 'stable-diffusion' directory is\n",
@ -21,7 +21,7 @@ This model card focuses on the model associated with the Stable Diffusion model,
# Uses
## Direct Use
## Direct Use
The model is intended for research purposes only. Possible research areas and
tasks include
@ -68,11 +68,11 @@ Using the model to generate content that is cruel to individuals is a misuse of
considerations.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
which consists of images that are primarily limited to English descriptions.
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
which consists of images that are primarily limited to English descriptions.
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
@ -84,7 +84,7 @@ The model developers used the following dataset for training the model:
- LAION-2B (en) and subsets thereof (see next section)
**Training Procedure**
Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
- Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
- Text prompts are encoded through a ViT-L/14 text-encoder.
@ -108,12 +108,12 @@ filtered to images with an original size `>= 512x512`, estimated aesthetics scor
- **Batch:** 32 x 8 x 2 x 4 = 2048
- **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
## Evaluation Results
## Evaluation Results
Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
steps show the relative improvements of the checkpoints:
Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores.
1. On CUDA systems, the 768 pixel stable-diffusion-2.0 and
stable-diffusion-2.1 models can only be run as `diffusers` models
when the `xformer` library is installed and configured. Without
`xformers`, InvokeAI returns black images.
2. Inpainting and outpainting have regressed in quality.
Both these issues are being actively worked on.
## v2.2.4 <small>(11 December 2022)</small>
**the `invokeai` directory**
Previously there were two directories to worry about, the directory that
contained the InvokeAI source code and the launcher scripts, and the `invokeai`
directory that contained the models files, embeddings, configuration and
outputs. With the 2.2.4 release, this dual system is done away with, and
everything, including the `invoke.bat` and `invoke.sh` launcher scripts, now
live in a directory named `invokeai`. By default this directory is located in
your home directory (e.g. `\Users\yourname` on Windows), but you can select
where it goes at install time.
After installation, you can delete the install directory (the one that the zip
file creates when it unpacks). Do **not** delete or move the `invokeai`
directory!
**Initialization file `invokeai/invokeai.init`**
You can place frequently-used startup options in this file, such as the default
number of steps or your preferred sampler. To keep everything in one place, this
file has now been moved into the `invokeai` directory and is named
`invokeai.init`.
**To update from Version 2.2.3**
The easiest route is to download and unpack one of the 2.2.4 installer files.
When it asks you for the location of the `invokeai` runtime directory, respond
with the path to the directory that contains your 2.2.3 `invokeai`. That is, if
`invokeai` lives at `C:\Users\fred\invokeai`, then answer with `C:\Users\fred`
and answer "Y" when asked if you want to reuse the directory.
The `update.sh` (`update.bat`) script that came with the 2.2.3 source installer
does not know about the new directory layout and won't be fully functional.
**To update to 2.2.5 (and beyond) there's now an update path**
As they become available, you can update to more recent versions of InvokeAI
using an `update.sh` (`update.bat`) script located in the `invokeai` directory.
Running it without any arguments will install the most recent version of
InvokeAI. Alternatively, you can get set releases by running the `update.sh`
script with an argument in the command shell. This syntax accepts the path to
the desired release's zip file, which you can find by clicking on the green
"Code" button on this repository's home page.
**Other 2.2.4 Improvements**
- Fix InvokeAI GUI initialization by @addianto in #1687
- fix link in documentation by @lstein in #1728
- Fix broken link by @ShawnZhong in #1736
- Remove reference to binary installer by @lstein in #1731
- documentation fixes for 2.2.3 by @lstein in #1740
- Modify installer links to point closer to the source installer by @ebr in
#1745
- add documentation warning about 1650/60 cards by @lstein in #1753
- Fix Linux source URL in installation docs by @andybearman in #1756
- Make install instructions discoverable in readme by @damian0815 in #1752
- typo fix by @ofirkris in #1755
- Non-interactive model download (support HUGGINGFACE_TOKEN) by @ebr in #1578
- fix(srcinstall): shell installer - cp scripts instead of linking by @tildebyte
in #1765
- stability and usage improvements to binary & source installers by @lstein in
#1760
- fix off-by-one bug in cross-attention-control by @damian0815 in #1774
- Eventually update APP_VERSION to 2.2.3 by @spezialspezial in #1768
- invoke script cds to its location before running by @lstein in #1805
- Make PaperCut and VoxelArt models load again by @lstein in #1730
- Fix --embedding_directory / --embedding_path not working by @blessedcoolant in
#1817
- Clean up readme by @hipsterusername in #1820
- Optimized Docker build with support for external working directory by @ebr in
#1544
- disable pushing the cloud container by @mauwii in #1831
- Fix docker push github action and expand with additional metadata by @ebr in
#1837
- Fix Broken Link To Notebook by @VedantMadane in #1821
- Account for flat models by @spezialspezial in #1766
- Update invoke.bat.in isolate environment variables by @lynnewu in #1833
- Arch Linux Specific PatchMatch Instructions & fixing conda install on linux by
@SammCheese in #1848
- Make force free GPU memory work in img2img by @addianto in #1844
- New installer by @lstein
## v2.2.3 <small>(2 December 2022)</small>
!!! Note
This point release removes references to the binary installer from the
installation guide. The binary installer is not stable at the current
time. First time users are encouraged to use the "source" installer as
described in [Installing InvokeAI with the Source Installer](installation/deprecated_documentation/INSTALL_SOURCE.md)
With InvokeAI 2.2, this project now provides enthusiasts and professionals a
robust workflow solution for creating AI-generated and human facilitated
compositions. Additional enhancements have been made as well, improving safety,
ease of use, and installation.
Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
512x768 image (and less for smaller images), and is compatible with
Windows/Linux/Mac (M1 & M2).
You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
introduces the main WebUI enhancement for version 2.2 -
[The Unified Canvas](features/UNIFIED_CANVAS.md). This new workflow is the
biggest enhancement added to the WebUI to date, and unlocks a stunning amount of
potential for users to create and iterate on their creations. The following
sections describe what's new for InvokeAI.
## v2.2.2 <small>(30 November 2022)</small>
!!! note
The binary installer is not ready for prime time. First time users are recommended to install via the "source" installer accessible through the links at the bottom of this page.****
With InvokeAI 2.2, this project now provides enthusiasts and professionals a
robust workflow solution for creating AI-generated and human facilitated
compositions. Additional enhancements have been made as well, improving safety,
ease of use, and installation.
Optimized for efficiency, InvokeAI needs only ~3.5GB of VRAM to generate a
512x768 image (and less for smaller images), and is compatible with
Windows/Linux/Mac (M1 & M2).
You can see the [release video](https://youtu.be/hIYBfDtKaus) here, which
introduces the main WebUI enhancement for version 2.2 -
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
