rattus 4e6a1b66a9 speed up and reduce VRAM of QWEN VAE and WAN (less so) (#12036) ... * ops: introduce autopad for conv3d This works around pytorch missing ability to causal pad as part of the kernel and avoids massive weight duplications for padding. * wan-vae: rework causal padding This currently uses F.pad which takes a full deep copy and is liable to be the VRAM peak. Instead, kick spatial padding back to the op and consolidate the temporal padding with the cat for the cache. * wan-vae: implement zero pad fast path The WAN VAE is also QWEN where it is used single-image. These convolutions are however zero padded 3d convolutions, which means the VAE is actually just 2D down the last element of the conv weight in the temporal dimension. Fast path this, to avoid adding zeros that then just evaporate in convoluton math but cost computation.		2026-01-23 19:56:14 -05:00
..
audio_encoders	…
cldm	…
comfy_types	…
extra_samplers	…
image_encoders	…
k_diffusion	Fix noise with ancestral samplers when inferencing on cpu. (#11528)	2025-12-26 22:03:01 -05:00
ldm	speed up and reduce VRAM of QWEN VAE and WAN (less so) (#12036)	2026-01-23 19:56:14 -05:00
sd1_tokenizer	…
t2i_adapter	…
taesd	Support LTX2 tiny vae (taeltx_2) (#11929)	2026-01-21 23:03:51 -05:00
text_encoders	Support loading flux 2 klein checkpoints saved with SaveCheckpoint. (#12033)	2026-01-22 18:20:48 -05:00
weight_adapter	…
checkpoint_pickle.py	…
cli_args.py	Add most basic Asset support for models (#11315)	2026-01-08 22:21:51 -05:00
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.py	Add image sizes to clip vision outputs. (#11923)	2026-01-16 23:02:28 -05:00
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_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	…
conds.py	…
context_windows.py	Add handling for vace_context in context windows (#11386)	2025-12-30 14:40:42 -08:00
controlnet.py	…
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 regular empty latent node work properly on flux 2 variants. (#12050)	2026-01-23 19:50:48 -05:00
lora.py	Support ModelScope-Trainer/DiffSynth LoRA format for Flux.2 Klein models (#12042)	2026-01-23 15:27:49 -05:00
lora_convert.py	…
model_base.py	qwen_image: propagate attention mask. (#11966)	2026-01-22 20:02:31 -05:00
model_detection.py	Support the Anima model. (#12012)	2026-01-21 19:44:28 -05:00
model_management.py	pythorch_attn_by_def_on_gfx1200 (#11793)	2026-01-10 16:51:05 -05:00
model_patcher.py	ops: Fix offloading with FP8MM performance (#11697)	2026-01-07 21:01:16 -05:00
model_sampling.py	…
nested_tensor.py	…
ops.py	speed up and reduce VRAM of QWEN VAE and WAN (less so) (#12036)	2026-01-23 19:56:14 -05:00
options.py	…
patcher_extension.py	…
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	skip_load_model -> force_full_load (#11390)	2025-12-17 23:29:32 -05:00
samplers.py	Support nested tensor denoise masks. (#11431)	2025-12-19 19:59:25 -05:00
sd.py	Support LTX2 tiny vae (taeltx_2) (#11929)	2026-01-21 23:03:51 -05:00
sd1_clip.py	Disable prompt weights on newbie te. (#11434)	2025-12-20 00:19:47 -05:00
sd1_clip_config.json	…
sdxl_clip.py	…
supported_models.py	Support loading flux 2 klein checkpoints saved with SaveCheckpoint. (#12033)	2026-01-22 18:20:48 -05:00
supported_models_base.py	Fix some custom nodes. (#11134)	2025-12-05 18:25:31 -05:00
utils.py	Add LyCoris LoKr MLP layer support for Flux2 (#11997)	2026-01-20 23:18:33 -05:00