mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
15b33ad501
Add support for FreeU. See: - https://huggingface.co/docs/diffusers/main/en/using-diffusers/freeu - https://github.com/ChenyangSi/FreeU Implementation: - `ModelPatcher.apply_freeu()` handles the enabling freeu (which is very simple with diffusers). - `FreeUConfig` model added to hold the hyperparameters. - `freeu_config` added as optional sub-field on `UNetField`. - `FreeUInvocation` added, works like LoRA - chain it to add the FreeU config to the UNet - No support for model-dependent presets, this will be a future workflow editor enhancement Closes #4845 |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| baseinvocation.py | ||
| collections.py | ||
| compel.py | ||
| controlnet_image_processors.py | ||
| cv.py | ||
| facetools.py | ||
| image.py | ||
| infill.py | ||
| ip_adapter.py | ||
| latent.py | ||
| math.py | ||
| metadata.py | ||
| model.py | ||
| noise.py | ||
| onnx.py | ||
| param_easing.py | ||
| primitives.py | ||
| prompt.py | ||
| sdxl.py | ||
| shared.py | ||
| strings.py | ||
| t2i_adapter.py | ||
| upscale.py | ||