| .. |
|
audio_encoders
|
models: Use CoreModelPatcher
|
2026-01-27 18:56:10 +10:00 |
|
cldm
|
|
|
|
comfy_types
|
|
|
|
extra_samplers
|
|
|
|
image_encoders
|
|
|
|
k_diffusion
|
sampling: improve progress meter accuracy for dynamic loading
|
2026-01-27 18:57:21 +10:00 |
|
ldm
|
models: Use CoreModelPatcher
|
2026-01-27 18:56:10 +10:00 |
|
sd1_tokenizer
|
|
|
|
t2i_adapter
|
|
|
|
taesd
|
Support LTX2 tiny vae (taeltx_2) (#11929)
|
2026-01-21 23:03:51 -05:00 |
|
text_encoders
|
clip: support assign load when taking clip from a ckpt
|
2026-01-27 18:57:21 +10:00 |
|
weight_adapter
|
[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958)
|
2026-01-24 22:56:22 -05:00 |
|
checkpoint_pickle.py
|
|
|
|
cli_args.py
|
main: Go live with --fast dynamic_vram
|
2026-01-27 18:56:50 +10:00 |
|
clip_config_bigg.json
|
|
|
|
clip_model.py
|
Support the siglip 2 naflex model as a clip vision model. (#11831)
|
2026-01-12 17:05:54 -05:00 |
|
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_siglip2_base_naflex.json
|
Support the siglip 2 naflex model as a clip vision model. (#11831)
|
2026-01-12 17:05:54 -05:00 |
|
clip_vision_siglip_384.json
|
|
|
|
clip_vision_siglip_512.json
|
|
|
|
clip_vision.py
|
models: Use CoreModelPatcher
|
2026-01-27 18:56:10 +10:00 |
|
conds.py
|
|
|
|
context_windows.py
|
|
|
|
controlnet.py
|
models: Use CoreModelPatcher
|
2026-01-27 18:56:10 +10:00 |
|
diffusers_convert.py
|
|
|
|
diffusers_load.py
|
|
|
|
float.py
|
Optimize nvfp4 lora applying. (#11866)
|
2026-01-14 00:49:38 -05:00 |
|
gligen.py
|
|
|
|
hooks.py
|
New Year ruff cleanup. (#11595)
|
2026-01-01 22:06:14 -05:00 |
|
latent_formats.py
|
Make empty latent node work with other models. (#12062)
|
2026-01-24 19:23:20 -05:00 |
|
lora_convert.py
|
|
|
|
lora.py
|
Support ModelScope-Trainer/DiffSynth LoRA format for Flux.2 Klein models (#12042)
|
2026-01-23 15:27:49 -05:00 |
|
memory_management.py
|
main: Rework aimdo into process
|
2026-01-27 18:57:21 +10:00 |
|
model_base.py
|
models: Use CoreModelPatcher
|
2026-01-27 18:56:10 +10:00 |
|
model_detection.py
|
Only enable fp16 on z image models that actually support it. (#12065)
|
2026-01-24 22:32:28 -05:00 |
|
model_management.py
|
mm: fix sync
|
2026-01-27 18:56:53 +10:00 |
|
model_patcher.py
|
ruff
|
2026-01-27 18:57:21 +10:00 |
|
model_sampling.py
|
|
|
|
nested_tensor.py
|
|
|
|
ops.py
|
ruff
|
2026-01-27 18:57:21 +10:00 |
|
options.py
|
|
|
|
patcher_extension.py
|
|
|
|
pinned_memory.py
|
ruff
|
2026-01-27 18:57:21 +10:00 |
|
pixel_space_convert.py
|
|
|
|
quant_ops.py
|
Optimize nvfp4 lora applying. (#11866)
|
2026-01-14 00:49:38 -05:00 |
|
rmsnorm.py
|
|
|
|
sample.py
|
Make regular empty latent node work properly on flux 2 variants. (#12050)
|
2026-01-23 19:50:48 -05:00 |
|
sampler_helpers.py
|
|
|
|
samplers.py
|
ruff
|
2026-01-27 18:57:21 +10:00 |
|
sd1_clip_config.json
|
|
|
|
sd1_clip.py
|
clip: support assign load when taking clip from a ckpt
|
2026-01-27 18:57:21 +10:00 |
|
sd.py
|
clip: support assign load when taking clip from a ckpt
|
2026-01-27 18:57:21 +10:00 |
|
sdxl_clip.py
|
|
|
|
supported_models_base.py
|
|
|
|
supported_models.py
|
Only enable fp16 on z image models that actually support it. (#12065)
|
2026-01-24 22:32:28 -05:00 |
|
utils.py
|
move string_to_seed to utils.py
|
2026-01-27 18:56:10 +10:00 |
3908056730