rattus 1a157e1f97 Reduce LTX VAE VRAM usage and save use cases from OOMs/Tiler (#13013) ... * ltx: vae: scale the chunk size with the users VRAM Scale this linearly down for users with low VRAM. * ltx: vae: free non-chunking recursive intermediates * ltx: vae: cleanup some intermediates The conv layer can be the VRAM peak and it does a torch.cat. So cleanup the pieces of the cat. Also clear our the cache ASAP as each layer detect its end as this VAE surges in VRAM at the end due to the ended padding increasing the size of the final frame convolutions off-the-books to the chunker. So if all the earlier layers free up their cache it can offset that surge. Its a fragmentation nightmare, and the chance of it having to recache the pyt allocator is very high, but you wont OOM.		2026-03-17 17:32:43 -04:00
..
audio_encoders	Fix fp16 audio encoder models (#12811)	2026-03-06 18:20:07 -05:00
cldm	Add better error message for common error. (#10846)	2025-11-23 04:55:22 -05:00
comfy_types	fix: use frontend-compatible format for Float gradient_stops (#12789)	2026-03-12 10:14:28 -07:00
extra_samplers
image_encoders
k_diffusion	ace15: Use dynamic_vram friendly trange (#12409)	2026-02-11 14:53:42 -05:00
ldm	Reduce LTX VAE VRAM usage and save use cases from OOMs/Tiler (#13013)	2026-03-17 17:32:43 -04:00
sd1_tokenizer
t2i_adapter
taesd	Support LTX2 tiny vae (taeltx_2) (#11929)	2026-01-21 23:03:51 -05:00
text_encoders	Support the LTXAV 2.3 model. (#12773)	2026-03-04 20:06:20 -05:00
weight_adapter	MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) (#12446)	2026-02-15 20:30:09 -05:00
cli_args.py	Add --enable-dynamic-vram options to force enable it. (#13002)	2026-03-16 16:50:13 -04:00
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	Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845)	2026-02-01 01:01:11 -05:00
conds.py	Cleanups to the last PR. (#12646)	2026-02-26 01:30:31 -05:00
context_windows.py	fix: handle substep sigmas in context window set_step (#12719)	2026-03-01 09:38:30 -08:00
controlnet.py	Add working Qwen 2512 ControlNet (Fun ControlNet) support (#12359)	2026-02-13 22:23:52 -05:00
diffusers_convert.py
diffusers_load.py
float.py	feat: Support mxfp8 (#12907)	2026-03-14 18:36:29 -04:00
gligen.py
hooks.py	New Year ruff cleanup. (#11595)	2026-01-01 22:06:14 -05:00
latent_formats.py	Feat: z-image pixel space (model still training atm) (#12709)	2026-03-02 19:43:47 -05:00
lora_convert.py	Use torch RMSNorm for flux models and refactor hunyuan video code. (#12432)	2026-02-13 15:35:13 -05:00
lora.py	Fix text encoder lora loading for wrapped models (#12852)	2026-03-09 16:08:51 -04:00
memory_management.py	comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups (#12925)	2026-03-13 22:18:08 -04:00
model_base.py	Support the LTXAV 2.3 model. (#12773)	2026-03-04 20:06:20 -05:00
model_detection.py	model_detection: deep clone pre edited edited weights (#12862)	2026-03-09 23:50:10 -04:00
model_management.py	Skip running model finalizers at exit (#12994)	2026-03-16 16:00:42 -04:00
model_patcher.py	comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups (#12925)	2026-03-13 22:18:08 -04:00
model_sampling.py	initial FlowRVS support (#12637)	2026-02-25 23:38:46 -05:00
nested_tensor.py	WIP way to support multi multi dimensional latents. (#10456)	2025-10-23 21:21:14 -04:00
ops.py	[Trainer] FP4, 8, 16 training by native dtype support and quant linear autograd function (#12681)	2026-03-16 21:31:50 -04:00
options.py
patcher_extension.py	Fix order of inputs nested merge_nested_dicts (#10362)	2025-10-15 16:47:26 -07:00
pinned_memory.py	comfy aimdo 0.2.11 + Improved RAM Pressure release strategies - Windows speedups (#12925)	2026-03-13 22:18:08 -04:00
pixel_space_convert.py	Changes to the previous radiance commit. (#9851)	2025-09-13 18:03:34 -04:00
quant_ops.py	feat: Support mxfp8 (#12907)	2026-03-14 18:36:29 -04:00
rmsnorm.py	Remove code to support RMSNorm on old pytorch. (#12499)	2026-02-16 20:09:24 -05:00
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	Disable dynamic_vram when weight hooks applied (#12653)	2026-02-28 16:50:18 -05:00
samplers.py	Disable dynamic_vram when weight hooks applied (#12653)	2026-02-28 16:50:18 -05:00
sd1_clip_config.json
sd1_clip.py	Force min length 1 when tokenizing for text generation. (#12538)	2026-02-19 22:57:44 -05:00
sd.py	Add --fp16-intermediates to use fp16 for intermediate values between nodes (#12953)	2026-03-14 19:18:19 -04:00
sdxl_clip.py
supported_models_base.py	Fix some custom nodes. (#11134)	2025-12-05 18:25:31 -05:00
supported_models.py	Adjust memory usage factor of zeta model. (#12746)	2026-03-03 17:35:22 -05:00
utils.py	Fix potential issue. (#13009)	2026-03-16 21:38:40 -04:00
windows.py	Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845)	2026-02-01 01:01:11 -05:00