298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-01-11 02:15:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
61b50720d0
ComfyUI/comfy
History
Raphael Walker 61b50720d0
Add support for attention masking in Flux (#5942) 
* fix attention OOM in xformers

* allow passing attention mask in flux attention

* allow an attn_mask in flux

* attn masks can be done using replace patches instead of a separate dict

* fix return types

* fix return order

* enumerate

* patch the right keys

* arg names

* fix a silly bug

* fix xformers masks

* replace match with if, elif, else

* mask with image_ref_size

* remove unused import

* remove unused import 2

* fix pytorch/xformers attention

This corrects a weird inconsistency with skip_reshape.
It also allows masks of various shapes to be passed, which will be
automtically expanded (in a memory-efficient way) to a size that is
compatible with xformers or pytorch sdpa respectively.

* fix mask shapes
2024-12-16 18:21:17 -05:00
..
cldm Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
comfy_types [Developer Experience] Add node typing (#5676) 2024-12-04 15:01:00 -05:00
extra_samplers Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
k_diffusion Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
ldm Add support for attention masking in Flux (#5942) 2024-12-16 18:21:17 -05:00
sd1_tokenizer Initial commit. 2023-01-16 22:37:14 -05:00
t2i_adapter Controlnet refactor. 2024-06-27 18:43:11 -04:00
taesd Improvements to the TAESD3 implementation. 2024-06-16 02:04:24 -04:00
text_encoders Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
checkpoint_pickle.py Remove pytorch_lightning dependency. 2023-06-13 10:11:33 -04:00
cli_args.py Add option to inference the diffusion model in fp32 and fp64. 2024-11-25 05:00:23 -05:00
clip_config_bigg.json Fix potential issue with non clip text embeddings. 2024-07-30 14:41:13 -04:00
clip_model.py Support new flux model variants. 2024-11-21 08:38:23 -05:00
clip_vision_config_g.json Add support for clip g vision model to CLIPVisionLoader. 2023-08-18 11:13:29 -04:00
clip_vision_config_h.json Add support for unCLIP SD2.x models. 2023-04-01 23:19:15 -04:00
clip_vision_config_vitl_336.json support clip-vit-large-patch14-336 (#4042) 2024-07-17 13:12:50 -04:00
clip_vision_config_vitl.json Add support for unCLIP SD2.x models. 2023-04-01 23:19:15 -04:00
clip_vision_siglip_384.json Support new flux model variants. 2024-11-21 08:38:23 -05:00
clip_vision.py Add a way to disable cropping in the CLIPVisionEncode node. 2024-11-28 20:24:47 -05:00
conds.py Fix bug with cosxl edit model. 2024-06-10 16:00:03 -04:00
controlnet.py Enforce all pyflake lint rules (#6033) 2024-12-12 19:29:37 -05:00
diffusers_convert.py Fix saving text encoder in fp8. 2024-04-02 11:46:34 -04:00
diffusers_load.py load_unet -> load_diffusion_model with a model_options argument. 2024-08-12 23:20:57 -04:00
float.py Clamp output when rounding weight to prevent Nan. 2024-10-19 19:07:10 -04:00
gligen.py Lint and fix undefined names (1/N) (#6028) 2024-12-12 18:55:26 -05:00
hooks.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
latent_formats.py Fast previews for ltxv. 2024-11-28 06:46:15 -05:00
lora_convert.py Support new flux model variants. 2024-11-21 08:38:23 -05:00
lora.py ModelPatcher Overhaul and Hook Support (#5583) 2024-12-02 14:51:02 -05:00
model_base.py Add support for attention masking in Flux (#5942) 2024-12-16 18:21:17 -05:00
model_detection.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
model_management.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
model_patcher.py Make ModelPatcher class clone function work with inheritance. 2024-12-03 13:57:57 -05:00
model_sampling.py Make timestep ranges more usable on rectified flow models. 2024-12-05 16:40:58 -05:00
ops.py clamp input (#5928) 2024-12-07 14:00:31 -05:00
options.py Only parse command line args when main.py is called. 2023-09-13 11:38:20 -04:00
patcher_extension.py Enforce all pyflake lint rules (#6033) 2024-12-12 19:29:37 -05:00
sample.py Reshape the empty latent image to the right amount of channels if needed. 2024-06-08 02:35:08 -04:00
sampler_helpers.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
samplers.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
sd1_clip_config.json Fix potential issue with non clip text embeddings. 2024-07-30 14:41:13 -04:00
sd1_clip.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
sd.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
sdxl_clip.py Long CLIP L support for SDXL, SD3 and Flux. 2024-09-15 07:59:38 -04:00
supported_models_base.py Mixed precision diffusion models with scaled fp8. 2024-10-21 18:12:51 -04:00
supported_models.py Lint all unused variables (#5989) 2024-12-12 17:59:16 -05:00
utils.py Add support for attention masking in Flux (#5942) 2024-12-16 18:21:17 -05:00