| .. |
|
cldm
|
|
|
|
comfy_types
|
[Type] Mark input options NotRequired (#7614)
|
2025-04-16 15:41:00 -04:00 |
|
extra_samplers
|
|
|
|
image_encoders
|
|
|
|
k_diffusion
|
Add SEEDS (stage 2 & 3 DP) sampler (#7580)
|
2025-04-12 18:36:08 -04:00 |
|
ldm
|
Set default context_img_len to 257
|
2025-04-17 12:42:34 -04:00 |
|
sd1_tokenizer
|
|
|
|
t2i_adapter
|
Controlnet refactor.
|
2024-06-27 18:43:11 -04:00 |
|
taesd
|
|
|
|
text_encoders
|
Use empty t5 of size 128 for hidream, seems to give closer results.
|
2025-04-19 19:49:40 -04:00 |
|
checkpoint_pickle.py
|
|
|
|
cli_args.py
|
Add CublasOps support (#7574)
|
2025-04-12 18:29:15 -04:00 |
|
clip_config_bigg.json
|
|
|
|
clip_model.py
|
|
|
|
clip_vision_config_g.json
|
|
|
|
clip_vision_config_h.json
|
|
|
|
clip_vision_config_vitl_336_llava.json
|
|
|
|
clip_vision_config_vitl_336.json
|
|
|
|
clip_vision_config_vitl.json
|
|
|
|
clip_vision_siglip_384.json
|
|
|
|
clip_vision_siglip_512.json
|
Support 512 siglip model.
|
2025-04-05 07:01:01 -04:00 |
|
clip_vision.py
|
Support 512 siglip model.
|
2025-04-05 07:01:01 -04:00 |
|
conds.py
|
|
|
|
controlnet.py
|
Slightly better fix for #7687
|
2025-04-20 11:33:27 -04:00 |
|
diffusers_convert.py
|
|
|
|
diffusers_load.py
|
|
|
|
float.py
|
|
|
|
gligen.py
|
|
|
|
hooks.py
|
|
|
|
latent_formats.py
|
Initial Hunyuan3Dv2 implementation.
|
2025-03-19 16:52:58 -04:00 |
|
lora_convert.py
|
Support the wan fun reward loras.
|
2025-04-07 05:01:47 -04:00 |
|
lora.py
|
|
|
|
model_base.py
|
Basic support for hidream i1 model.
|
2025-04-15 17:35:05 -04:00 |
|
model_detection.py
|
Support loading WAN FLF model.
|
2025-04-17 12:04:48 -04:00 |
|
model_management.py
|
MLU memory optimization (#7470)
|
2025-04-02 19:24:04 -04:00 |
|
model_patcher.py
|
|
|
|
model_sampling.py
|
Automatically set the right sampling type for lotus.
|
2025-03-21 14:19:37 -04:00 |
|
ops.py
|
Basic support for hidream i1 model.
|
2025-04-15 17:35:05 -04:00 |
|
options.py
|
|
|
|
patcher_extension.py
|
Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape (#7500)
|
2025-04-09 09:43:35 -04:00 |
|
rmsnorm.py
|
Fix issue on old torch.
|
2025-04-16 04:53:56 -04:00 |
|
sample.py
|
|
|
|
sampler_helpers.py
|
Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape (#7500)
|
2025-04-09 09:43:35 -04:00 |
|
samplers.py
|
Add SEEDS (stage 2 & 3 DP) sampler (#7580)
|
2025-04-12 18:36:08 -04:00 |
|
sd1_clip_config.json
|
|
|
|
sd1_clip.py
|
More flexible long clip support.
|
2025-04-15 10:32:21 -04:00 |
|
sd.py
|
Hidream: Allow loading hidream text encoders in CLIPLoader and DualCLIPLoader (#7676)
|
2025-04-19 19:47:30 -04:00 |
|
sdxl_clip.py
|
More flexible long clip support.
|
2025-04-15 10:32:21 -04:00 |
|
supported_models_base.py
|
|
|
|
supported_models.py
|
Basic support for hidream i1 model.
|
2025-04-15 17:35:05 -04:00 |
|
utils.py
|
|
|
