- 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
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
- 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.
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
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.
- 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.
- 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
- 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>
- 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.
* 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
* 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) 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
* Add Embedding Parsing
* Add Embedding Parsing
* Return token_dim in embedding_info
* fixes to handle other variants
1. Handle the case of a .bin file being mislabeled .pt (seen in the
wild at https://cyberes.github.io/stable-diffusion-textual-inversion-models/)
2. Handle the "broken" .pt files reported by https://github.com/invoke-ai/InvokeAI/issues/1829
3. When token name is not available, use the basename of the pt or bin file rather than the
whole path.
fixes#1829
* remove whitespace
Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>
* 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.
* 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.
- 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>
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.
