395 Commits

Author	SHA1	Message	Date
Yousef R. Gamaleldin	ce0c979e96	Merge 553f71aa9e into fc1fdf3389	2026-03-28 18:06:24 +00:00
rattus	b353a7c863	Integrate RAM cache with model RAM management (#13173)	2026-03-27 21:34:16 -04:00
Jukka Seppänen	404d7b9978	feat: Support Qwen3.5 text generation models (#12771)	2026-03-25 22:48:28 -04:00
rattus	82b868a45a	Fix VRAM leak in tiler fallback in video VAEs (#13073) ... * sd: soft_empty_cache on tiler fallback This doesnt cost a lot and creates the expected VRAM reduction in resource monitors when you fallback to tiler. * wan: vae: Don't recursion in local fns (move run_up) Moved Decoder3d’s recursive run_up out of forward into a class method to avoid nested closure self-reference cycles. This avoids cyclic garbage that delays garbage of tensors which in turn delays VRAM release before tiled fallback. * ltx: vae: Don't recursion in local fns (move run_up) Mov the recursive run_up out of forward into a class method to avoid nested closure self-reference cycles. This avoids cyclic garbage that delays garbage of tensors which in turn delays VRAM release before tiled fallback.	2026-03-19 22:30:27 -04:00
Yousef R. Gamaleldin	3bd7d8b15d	Merge branch 'master' into seedvr2	2026-03-20 03:39:56 +02:00
Yousef Rafat	af6c5d6de9	tested with a modern version of comfyui	2026-03-19 21:09:11 +02:00
rattus	fabed694a2	ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reductions) (#13062) ... * ltx: vae: add cache state to downsample block * ltx: vae: Add time stride awareness to causal_conv_3d * ltx: vae: Automate truncation for encoder Other VAEs just truncate without error. Do the same. * sd/ltx: Make chunked_io a flag in its own right Taking this bi-direcitonal, so make it a for-purpose named flag. * ltx: vae: implement chunked encoder + CPU IO chunking People are doing things with big frame counts in LTX including V2V flows. Implement the time-chunked encoder to keep the VRAM down, with the converse of the new CPU pre-allocation technique, where the chunks are brought from the CPU JIT. * ltx: vae-encode: round chunk sizes more strictly Only powers of 2 and multiple of 8 are valid due to cache slicing.	2026-03-19 09:58:47 -07:00
Yousef R. Gamaleldin	a1257d0426	Merge branch 'master' into seedvr2	2026-03-19 14:16:59 +02:00
Jukka Seppänen	9fff091f35	Further Reduce LTX VAE decode peak RAM usage (#13052)	2026-03-18 18:32:26 -04:00
comfyanonymous	68d542cc06	Fix case where pixel space VAE could cause issues. (#13030)	2026-03-17 20:46:22 -04:00
Jukka Seppänen	735a0465e5	Inplace VAE output processing to reduce peak RAM consumption. (#13028)	2026-03-17 20:20:49 -04:00
comfyanonymous	c711b8f437	Add --fp16-intermediates to use fp16 for intermediate values between nodes (#12953) ... This is an experimental WIP option that might not work in your workflow but should lower memory usage if it does. Currently only the VAE and the load image node will output in fp16 when this option is turned on.	2026-03-14 19:18:19 -04:00
rattus	535c16ce6e	Widen OOM_EXCEPTION to AcceleratorError form (#12835) ... Pytorch only filters for OOMs in its own allocators however there are paths that can OOM on allocators made outside the pytorch allocators. These manifest as an AllocatorError as pytorch does not have universal error translation to its OOM type on exception. Handle it. A log I have for this also shows a double report of the error async, so call the async discarder to cleanup and make these OOMs look like OOMs.	2026-03-10 00:41:02 -04:00
comfyanonymous	43c64b6308	Support the LTXAV 2.3 model. (#12773)	2026-03-04 20:06:20 -05:00
Jukka Seppänen	0a7446ade4	Pass tokens when loading text gen model for text generation (#12755) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-03-04 08:59:56 -08:00
rattus	5f41584e96	Disable dynamic_vram when weight hooks applied (#12653) ... * sd: add support for clip model reconstruction * nodes: SetClipHooks: Demote the dynamic model patcher * mp: Make dynamic_disable more robust The backup need to not be cloned. In addition add a delegate object to ModelPatcherDynamic so that non-cloning code can do ModelPatcherDynamic demotion * sampler_helpers: Demote to non-dynamic model patcher when hooking * code rabbit review comments	2026-02-28 16:50:18 -05:00
Talmaj	ac4412d0fa	Native LongCat-Image implementation (#12597)	2026-02-27 23:04:34 -05:00
Jukka Seppänen	907e5dcbbf	initial FlowRVS support (#12637)	2026-02-25 23:38:46 -05:00
rattus	3ebe1ac22e	Disable dynamic_vram when using torch compiler (#12612) ... * mp: attach re-construction arguments to model patcher When making a model-patcher from a unet or ckpt, attach a callable function that can be called to replay the model construction. This can be used to deep clone model patcher WRT the actual model. Originally written by Kosinkadink f4b99bc623 * mp: Add disable_dynamic clone argument Add a clone argument that lets a caller clone a ModelPatcher but disable dynamic to demote the clone to regular MP. This is useful for legacy features where dynamic_vram support is missing or TBD. * torch_compile: disable dynamic_vram This is a bigger feature. Disable for the interim to preserve functionality.	2026-02-24 19:13:46 -05:00
comfyanonymous	0301ccf745	Small cleanup and try to get qwen 3 work with the text gen. (#12537)	2026-02-19 22:42:28 -05:00
Jukka Seppänen	6d11cc7354	feat: Add basic text generation support with native models, initially supporting Gemma3 (#12392)	2026-02-18 20:49:43 -05:00
rattus	f719f9c062	sd: delay VAE dtype archive until after override (#12388) ... VAEs have host specific dtype logic that should override the dynamic _model_dtype. Defer the archiving of model dtypes until after.	2026-02-10 13:37:46 -05:00
comfyanonymous	35183543e0	Add VAE tiled decode node for audio. (#12299)	2026-02-05 01:12:04 -05:00
comfyanonymous	fe2511468d	Support the 4B ace step 1.5 lm model. (#12257) ... Can be used as an alternative to the 1.7B	2026-02-03 19:01:38 -05:00
comfyanonymous	b8315e66cb	Fix tiled vae for ace step 1.5 (#12253)	2026-02-03 14:40:45 -05:00
comfyanonymous	3c1a1a2df8	Basic support for the ace step 1.5 model. (#12237)	2026-02-03 00:06:18 -05:00
rattus	f8acd9c402	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
Kohaku-Blueleaf	a97c98068f	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) ... * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	2026-01-24 22:56:22 -05:00
Jukka Seppänen	3365ad18a5	Support LTX2 tiny vae (taeltx_2) (#11929)	2026-01-21 23:03:51 -05:00
comfyanonymous	abe2ec26a6	Support the Anima model. (#12012)	2026-01-21 19:44:28 -05:00
Yousef R. Gamaleldin	5f625fcc78	Merge branch 'master' into seedvr2	2026-01-17 17:08:13 +02:00
comfyanonymous	3b832231bb	Flux2 Klein support. (#11890)	2026-01-15 10:33:15 -05:00
comfyanonymous	cd912963f1	Fix issue with t5 text encoder in fp4. (#11794)	2026-01-10 17:31:31 -05:00
Yousef R. Gamaleldin	a506be2486	Merge branch 'master' into seedvr2	2026-01-09 01:00:06 +02:00
comfyanonymous	50d6e1caf4	Tweak ltxv vae mem estimation. (#11722)	2026-01-07 23:07:05 -05:00
comfyanonymous	25bc1b5b57	Add memory estimation function to ltxav text encoder. (#11716)	2026-01-07 20:11:22 -05:00
Yousef R. Gamaleldin	dbf8f9dcf9	Merge branch 'master' into seedvr2	2026-01-07 11:57:40 +02:00
comfyanonymous	f2b002372b	Support the LTXV 2 model. (#11632)	2026-01-05 01:58:59 -05:00
Yousef Rafat	31d358c78c	rope, attetntion update | vae on cpu warning	2026-01-04 19:15:53 +02:00
Yousef Rafat	49febe15c3	Merge branch 'seedvr2' of https://github.com/yousef-rafat/ComfyUI into seedvr2	2025-12-30 18:45:13 +02:00
Yousef Rafat	84fa155071	fixed manual vae loading	2025-12-30 18:44:57 +02:00
Jedrzej Kosinski	4691717340	Merge branch 'master' into seedvr2	2025-12-29 19:00:13 -08:00
Yousef Rafat	4fe772fae9	improvements	2025-12-20 23:20:45 +02:00
woctordho	4c432c11ed	Implement Jina CLIP v2 and NewBie dual CLIP (#11415) ... * Implement Jina CLIP v2 * Support quantized Gemma in NewBie dual CLIP	2025-12-20 00:57:22 -05:00
comfyanonymous	6a2678ac65	Trim/pad channels in VAE code. (#11406)	2025-12-18 18:22:38 -05:00
comfyanonymous	e4fb3a3572	Support loading Wan/Qwen VAEs with different in/out channels. (#11405)	2025-12-18 17:45:33 -05:00
Yousef R. Gamaleldin	183b377588	Merge branch 'master' into seedvr2	2025-12-17 00:39:06 +02:00
Farshore	e711aaf1a7	Lower VAE loading requirements：Create a new branch for GPU memory calculations in qwen-image vae (#11199)	2025-12-10 22:02:26 -05:00
Yousef Rafat	d12702ee0b	fixed some issues	2025-12-09 23:54:56 +02:00
rattus	e136b6dbb0	dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171) ... * make setattr safe for non existent attributes Handle the case where the attribute doesnt exist by returning a static sentinel (distinct from None). If the sentinel is passed in as the set value, del the attr. * Account for dequantization and type-casts in offload costs When measuring the cost of offload, identify weights that need a type change or dequantization and add the size of the conversion result to the offload cost. This is mutually exclusive with lowvram patches which already has a large conservative estimate and wont overlap the dequant cost so\ dont double count. * Set the compute type on CLIP MPs So that the loader can know the size of weights for dequant accounting.	2025-12-08 23:21:31 -05:00