wuyingwen/comfyui
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity
comfyui/comfy
History
FeepingCreature 7aceb9f91c
Add --use-flash-attention flag. (#7223) 
* Add --use-flash-attention flag.
This is useful on AMD systems, as FA builds are still 10% faster than Pytorch cross-attention.
2025-03-14 03:22:41 -04:00
..
cldm
Replace print with logging (#6138)
2024-12-20 16:24:55 -05:00
comfy_types
[NodeDef] Add documentation on multi_select input option (#7212)
2025-03-12 17:29:39 -04:00
extra_samplers
Uni pc sampler now works with audio and video models.
2025-01-18 05:27:58 -05:00
k_diffusion
Ensure the extra_args in dpmpp sde series (#7204)
2025-03-12 17:28:59 -04:00
ldm
Add --use-flash-attention flag. (#7223)
2025-03-14 03:22:41 -04:00
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
Add an image_interleave option to the Hunyuan image to video encode node.
2025-03-07 19:56:26 -05:00
checkpoint_pickle.py
Remove pytorch_lightning dependency.
2023-06-13 10:11:33 -04:00
cli_args.py
Add --use-flash-attention flag. (#7223)
2025-03-14 03:22:41 -04:00
clip_config_bigg.json
Fix potential issue with non clip text embeddings.
2024-07-30 14:41:13 -04:00
clip_model.py
Support llava clip vision model.
2025-03-06 00:24:43 -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_llava.json
Support llava clip vision model.
2025-03-06 00:24:43 -05:00
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
Support llava clip vision model.
2025-03-06 00:24:43 -05:00
conds.py
Remove unused function lcm in conds.py (#6572)
2025-01-23 05:54:09 -05:00
controlnet.py
Use fp16 if checkpoint weights are fp16 and the model supports it.
2025-02-27 16:39:57 -05:00
diffusers_convert.py
Remove useless code.
2025-01-24 06:15:54 -05:00
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
Hooks Part 2 - TransformerOptionsHook and AdditionalModelsHook (#6377)
2025-01-11 12:20:23 -05:00
latent_formats.py
Add fast preview support for Wan models.
2025-02-26 08:56:23 -05:00
lora_convert.py
Support new flux model variants.
2024-11-21 08:38:23 -05:00
lora.py
Only use stable cascade lora format with cascade model.
2025-02-01 06:35:22 -05:00
model_base.py
Support control loras on Wan.
2025-03-10 17:23:13 -04:00
model_detection.py
Support fp8_scaled diffusion models that don't use fp8 matrix mult.
2025-03-07 04:39:21 -05:00
model_management.py
Add --use-flash-attention flag. (#7223)
2025-03-14 03:22:41 -04:00
model_patcher.py
When cached_hook_patches contain weights for hooks, only use hook_backup for unused keys (#7067)
2025-03-09 04:26:31 -04:00
model_sampling.py
Allow batch of different sigmas when noise scaling.
2025-01-30 06:49:52 -05:00
ops.py
No need for scale_input when fp8 matrix mult is disabled.
2025-03-07 04:49:20 -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
Add ruff rule for empty line with trailing whitespace.
2024-12-28 05:23:08 -05:00
sample.py
Auto reshape 2d to 3d latent for single image generation on video model.
2024-12-29 02:26:49 -05:00
sampler_helpers.py
Cleanup old TODO.
2025-01-20 03:44:13 -05:00
samplers.py
Add er_sde sampler (#7187)
2025-03-12 02:42:37 -04:00
sd1_clip_config.json
Fix potential issue with non clip text embeddings.
2024-07-30 14:41:13 -04:00
sd1_clip.py
Fix some things breaking when embeddings fail to apply.
2025-03-06 13:31:55 -05:00
sd.py
Support LTXV 0.9.5.
2025-03-05 00:13:49 -05:00
sdxl_clip.py
Make it easier to set a custom template for hunyuan video.
2025-03-04 09:26:05 -05:00
supported_models_base.py
Mixed precision diffusion models with scaled fp8.
2024-10-21 18:12:51 -04:00
supported_models.py
Set WAN default compute dtype to fp16.
2025-03-07 04:52:36 -05:00
utils.py
Support LTXV 0.9.5.
2025-03-05 00:13:49 -05:00