InvokeAI/invokeai/backend
Ryan Dick b63df9bab9 wip
2024-08-26 20:17:50 -04:00
..
image_util Merge branch 'main' into depth_anything_v2 2024-08-03 00:38:57 +05:30
ip_adapter fix(backend): revert non-blocking device transfer 2024-07-16 08:59:42 +10:00
model_hash Run ruff 2024-06-26 21:46:59 +10:00
model_manager Update HF download logic to work for black-forest-labs/FLUX.1-schnell. 2024-08-26 20:17:50 -04:00
onnx fix(backend): revert non-blocking device transfer 2024-07-16 08:59:42 +10:00
quantization Make quantized loading fast for both T5XXL and FLUX transformer. 2024-08-26 20:17:50 -04:00
stable_diffusion Split a FluxTextEncoderInvocation out from the FluxTextToImageInvocation. This has the advantage that we benfit from automatic caching when the prompt isn't changed. 2024-08-26 20:17:50 -04:00
tiles feat(nodes): extract LATENT_SCALE_FACTOR to constants.py 2024-03-01 10:42:33 +11:00
util Update imports for compatibility with bumped diffusers version. 2024-08-26 20:17:50 -04:00
__init__.py consolidate model manager parts into a single class 2024-03-01 10:42:33 +11:00
bnb.py wip 2024-08-26 20:17:50 -04:00
load_flux_model_bnb_llm_int8.py wip 2024-08-26 20:17:50 -04:00
load_flux_model_bnb_nf4.py wip 2024-08-26 20:17:50 -04:00
load_flux_model.py WIP - experimentation 2024-08-26 20:17:50 -04:00
lora.py Remove tmp code 2024-08-07 22:06:05 -04:00
model_patcher.py Optimize weights handling 2024-07-30 03:39:01 +03:00
raw_model.py Merge branch 'main' into ryan/spandrel-upscale 2024-07-16 15:14:08 -04:00
requantize.py Make quantized loading fast. 2024-08-26 20:17:50 -04:00
spandrel_image_to_image_model.py Add tiling support to the SpoandrelImageToImage node. 2024-07-10 14:25:19 -04:00
textual_inversion.py fix(backend): revert non-blocking device transfer 2024-07-16 08:59:42 +10:00