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.
- 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.
- 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
* 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>
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()
```
- 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.
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.
- 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.
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.
- 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
