comfyanonymous 9da397ea2f Disable torch compiler for cast_bias_weight function (#10384) ... * Disable torch compiler for cast_bias_weight function * Fix torch compile.		2025-10-17 20:03:28 -04:00
..
audio_encoders	…
cldm	…
comfy_types	…
extra_samplers	…
image_encoders	…
k_diffusion	…
ldm	WAN2.2: Fix cache VRAM leak on error (#10308)	2025-10-13 15:23:11 -04:00
sd1_tokenizer	…
t2i_adapter	…
taesd	…
text_encoders	Implement gemma 3 as a text encoder. (#10241)	2025-10-06 22:08:08 -04:00
weight_adapter	…
checkpoint_pickle.py	…
cli_args.py	…
clip_config_bigg.json	…
clip_model.py	…
clip_vision.py	…
clip_vision_config_g.json	…
clip_vision_config_h.json	…
clip_vision_config_vitl.json	…
clip_vision_config_vitl_336.json	…
clip_vision_config_vitl_336_llava.json	…
clip_vision_siglip_384.json	…
clip_vision_siglip_512.json	…
conds.py	…
context_windows.py	…
controlnet.py	…
diffusers_convert.py	…
diffusers_load.py	…
float.py	…
gligen.py	…
hooks.py	…
latent_formats.py	…
lora.py	…
lora_convert.py	…
model_base.py	Always set diffusion model to eval() mode. (#10331)	2025-10-13 14:57:27 -04:00
model_detection.py	Implement gemma 3 as a text encoder. (#10241)	2025-10-06 22:08:08 -04:00
model_management.py	gfx942 doesn't support fp8 operations. (#10348)	2025-10-15 00:21:11 -04:00
model_patcher.py	Fix bug with applying loras on fp8 scaled without fp8 ops. (#10279)	2025-10-09 19:02:40 -04:00
model_sampling.py	Refactor model sampling sigmas code. (#10250)	2025-10-08 17:49:02 -04:00
ops.py	Disable torch compiler for cast_bias_weight function (#10384)	2025-10-17 20:03:28 -04:00
options.py	…
patcher_extension.py	Fix order of inputs nested merge_nested_dicts (#10362)	2025-10-15 16:47:26 -07:00
pixel_space_convert.py	…
rmsnorm.py	…
sample.py	…
sampler_helpers.py	…
samplers.py	refactor: Replace manual patches merging with merge_nested_dicts (#10360)	2025-10-15 17:16:09 -07:00
sd.py	Better memory estimation for the SD/Flux VAE on AMD. (#10334)	2025-10-13 22:37:19 -04:00
sd1_clip.py	…
sd1_clip_config.json	…
sdxl_clip.py	…
supported_models.py	Lower wan memory estimation value a bit. (#9964)	2025-09-20 22:09:35 -04:00
supported_models_base.py	…
utils.py	Fix loading old stable diffusion ckpt files on newer numpy. (#10333)	2025-10-13 22:18:58 -04:00