2261 Commits

Author	SHA1	Message	Date
ozbayb	75e8e4b6dc	Update compute_guide_overlap to include keyframe indices and temporal downscale ratio instead of using latent_start key added to attention_guide_entries. ... - This makes it possible for existing nodes like the ComfyUI-LTXVideo nodes to work with context windows without needing modifications	2026-05-05 22:46:52 -06:00
ozbayb	cbe2a1ba42	Fix guide keyframe misalignment when causal_window_fix is on with full guides	2026-05-05 21:52:34 -06:00
Talmaj	78b3096bf3	Void model - pass 1 & 2 (CORE-38) (#13403)	2026-05-05 19:59:04 -07:00
ozbayb	e0ea2e41c8	Merge remote-tracking branch 'origin/master' into 20260322a_ltx_contextwin	2026-05-05 20:14:21 -06:00
drozbay	e5369c0eec	feat: Context windows - add causal_window_fix to improve blending of context windows (CORE-100) (#13563) ... * Context windows: add causal_window_fix toggle * Fix slice_cond to correctly handle causal anchor index for temporal offsets	2026-05-05 16:40:53 -07:00
drozbay	1655f8089a	Add temporal_downscale_ratio to LatentFormat (#13702) ... Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com> Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com> Co-authored-by: Jukka Seppänen <40791699+kijai@users.noreply.github.com> Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-05-05 16:30:00 -07:00
Talmaj	fed8d5efa6	feat: Auto-regressive video generation (CORE-25) (#13082)	2026-05-04 21:01:22 -07:00
Jedrzej Kosinski	e758594e3b	Add deploy environment header (Comfy-Env) to partner node API calls (#13425)	2026-05-04 20:17:56 -07:00
Jedrzej Kosinski	ae457da84b	feat: add generic --feature-flag CLI arg and --list-feature-flags registry (#13685)	2026-05-04 19:50:26 -07:00
rattus	1265955b34	ops: handle multi-compute of the same weight (#13705) ... If the same weight is used multiple times within the same prefetch window, it should only apply compute state mutations once. Mark the weight as fully resident on the first pass accordingly.	2026-05-04 16:40:57 -07:00
rattus	1ac78180b3	make control-net load order deterministic (#13701) ... Make this deterministic so speeds dont change base of load order. Load them in reverse order so whatever the caller lists first is the top priority.	2026-05-04 12:58:06 -07:00
rattus	c47633f3be	prefetch: guard against no offload (#13703) ... cast_ will return no stream if there is no work to do. guard against this is the consume logic.	2026-05-04 12:56:05 -07:00
Silver	b138133ffa	Enable triton comfy kitchen via cli-arg (#12730)	2026-05-03 14:07:21 -04:00
Jukka Seppänen	be95871adc	feat: Gemma4 text generation support (CORE-30) (#13376) ... * initial gemma4 support * parity with reference implementation outputs can 100% match transformers with same sdpa flags, checkpoint this and then optimize * Cleanup, video fixes * cleanup, enable fused rms norm by default * update comment * Cleanup * Update sd.py * Various fixes * Add fp8 scaled embedding support * small fixes * Translate think tokens * Fix image encoder attention mask type So it works with basic attention * Handle thinking tokens different only for Gemma4 * Code cleanup * Update nodes_textgen.py * Use embed scale class instead of buffer Slight difference to HF, but technically more accurate and simpler code * Default to fused rms_norm * Update gemma4.py	2026-05-02 22:46:15 -04:00
rattus	783782d5d7	Implement block prefetch + Lora Async load + and adopt in LTX (Speedup!) (CORE-111) (#13618) ... * mm: Use Aimdo raw allocator for cast buffers pytorch manages allocation of growing buffers on streams poorly. Pyt has no windows support for the expandable segments allocator (which is the right tool for this job), while also segmenting the memory by stream such that it can be generally re-used. So kick the problem to aimdo which can just grow a virtual region thats freed per stream. * plan * ops: move cpu handler up to the caller * ops: split up prefetch from weight prep block prefetching API Split up the casting and weight formating/lora stuff in prep for arbitrary prefetch support. * ops: implement block prefetching API allow a model to construct a prefetch list and operate it for increased async offload. * ltxv2: Implement block prefetching * Implement lora async offload Implement async offload of loras.	2026-05-02 19:23:24 -04:00
Simon Lui	63103d519e	Remove IPEX and clean up checks and add missing synchronize during empty cache. (#13653)	2026-05-01 14:16:41 -07:00
Talmaj	cf9cbec596	Reformat models variable into multiline array CORE-59 (#13513) ... Co-authored-by: Talmaj Marinc <talmaj@comfy.org>	2026-05-01 17:20:11 +08:00
Rainer	e9c311b245	OneTainer ERNIE LoRA support (#13640)	2026-04-30 19:33:41 -04:00
blepping	a164c82913	Add high quality preview support for Flux2 latents (#13496)	2026-04-29 19:37:30 -04:00
Talmaj	5eeae3f1d8	Cogvideox (#13402) ... --------- Co-authored-by: kijai <40791699+kijai@users.noreply.github.com> Co-authored-by: Talmaj Marinc <talmaj@comfy.org>	2026-04-29 19:30:08 -04:00
Jukka Seppänen	0e25a6936e	Reduce video tiny VAE peak VRAM and decode time (CORE-127) (#13617) ... * Update taehv.py * Simplify * Simplify pixel_unshuffle dispatch	2026-04-29 12:15:10 -07:00
rattus	fce0398470	dynamicVRAM + --cache-ram 2 (CORE-117) (#13603) ... * pinned_memory: remove JIT RAM pressure release This doesn't work, as freeing intermediates for pins needs to be higher-priority than freeing pins-for-pins if and when you are going to do that. So this is too late as pins-for-pins is model load time and we dont have JIT pins-for-pins. * cacheing: Add a filter to only free intermediates from inactive wfs This is to get priorities in amongst pins straight. * mm: free inactive-ram from RAM cache first Stuff from inactive workflows should be freed before anything else. * caching: purge old ModelPatchers first Dont try and score them, just dump them at the first sign of trouble if they arent part of the workflow.	2026-04-28 19:15:02 -04:00
rattus	b47f15f25a	fix: Handle un-inited meta-tensors in models (fixes a CPU TE crash) (CORE-67) (#13578)	2026-04-27 22:22:31 -04:00
drozbay	f959e6bfa1	Merge branch 'master' into 20260322a_ltx_contextwin	2026-04-26 17:01:18 -06:00
ozbayb	4e434bccaa	Create separate latent_retain_index_list to ensure that inplace latent retention doesn't occur on all models when unintended.	2026-04-24 09:47:49 -06:00
Jukka Seppänen	084e08c6e2	Disable sageattention for SAM3 (#13529) ... Causes Nans	2026-04-23 11:14:42 -07:00
Jukka Seppänen	749d5b4e8d	feat: SAM (segment anything) 3.1 support (CORE-34) (#13408)	2026-04-23 00:07:43 -04:00
rattus	ec4b1659ab	ModelPatcherDynamic: force cast stray weights on comfy layers (#13487) ... the mixed_precision ops can have input_scale parameters that are used in tensor math but arent a weight or bias so dont get proper VRAM management. Treat these as force-castable parameters like the non comfy weight, random params are buffers already are.	2026-04-22 18:13:38 -04:00
blepping	9949c19c63	Derive InterruptProcessingException from BaseException (#13523)	2026-04-22 18:08:19 -04:00
Octopus	cc6f9500a1	fix: use Parameter assignment for Stable_Zero123 cc_projection weights (fixes #13492) (#13518) ... On Windows with aimdo enabled, disable_weight_init.Linear uses lazy initialization that sets weight and bias to None to avoid unnecessary memory allocation. This caused a crash when copy_() was called on the None weight attribute in Stable_Zero123.__init__. Replace copy_() with direct torch.nn.Parameter assignment, which works correctly on both Windows (aimdo enabled) and other platforms.	2026-04-22 15:05:43 -07:00
Jukka Seppänen	eb22225387	Support standalone LTXV audio VAEs (#13499)	2026-04-21 10:46:37 -07:00
comfyanonymous	ad94d47221	Make the ltx audio vae more native. (#13486)	2026-04-21 11:02:42 -04:00
comfyanonymous	3d816db07f	Some optimizations to make Ernie inference a bit faster. (#13472)	2026-04-18 23:02:29 -04:00
Jukka Seppänen	b9dedea57d	feat: SUPIR model support (CORE-17) (#13250)	2026-04-18 23:02:01 -04:00
Bedovyy	b41ab53b6f	Use ErnieTEModel_ not ErnieTEModel. (#13431)	2026-04-16 10:11:58 -04:00
Jun Yamog	1de83f91c3	Fix OOM regression in _apply() for quantized models during inference (#13372) ... Skip unnecessary clone of inference-mode tensors when already inside torch.inference_mode(), matching the existing guard in set_attr_param. The unconditional clone introduced in 20561aa9 caused transient VRAM doubling during model movement for FP8/quantized models.	2026-04-15 02:10:36 -07:00
comfyanonymous	cb0bbde402	Fix ernie on devices that don't support fp64. (#13414)	2026-04-14 22:54:47 -04:00
comfyanonymous	722bc73319	Make text generation work with ministral model. (#13395) ... Needs template before it works properly.	2026-04-13 20:43:57 -04:00
ozbayb	6442392810	Add defensive dtype cast before sigma step check	2026-04-13 15:19:25 -06:00
comfyanonymous	402ff1cdb7	Fix issue with ernie image. (#13393)	2026-04-13 16:38:42 -04:00
comfyanonymous	c2657d5fb9	Fix typo. (#13382)	2026-04-12 23:37:13 -04:00
ozbayb	6a53695006	LTX2 context windows - Skip guide frames in freenoise shuffle	2026-04-12 20:18:10 -06:00
ozbayb	a8b084ed58	LTX2 context windows - Thread per-modality overlap into fuse weights	2026-04-12 18:42:45 -06:00
ozbayb	f72583d1f3	LTX2 context windows - Move symmetric_patchifier import to module level	2026-04-12 15:46:20 -06:00
ozbayb	d59d6fb7a0	LTX2 context windows - Skip VRAM estimate clamp for packed latents	2026-04-12 15:43:36 -06:00
ozbayb	b348c7fa61	Merge branch '20260322a_ltx_contextwin' of https://github.com/drozbay/ComfyUI into 20260322a_ltx_contextwin	2026-04-12 14:54:00 -06:00
ozbayb	f1f3182be1	LTX2 context windows - Fix audio index mapping for wrapped/strided primary windows ... The previous window-level calculation collapsed wrapped or strided primary windows into a contiguous audio tail, so audio attended to a different temporal region than the video. Replace with per-frame mapping that computes each primary index's audio span independently and concatenates in order.	2026-04-12 14:52:54 -06:00
drozbay	32e9e4a694	Merge branch 'master' into 20260322a_ltx_contextwin	2026-04-12 12:22:31 -06:00
comfyanonymous	31283d2892	Implement Ernie Image model. (#13369)	2026-04-11 22:29:31 -04:00
comfyanonymous	55ebd287ee	Add a supports_fp64 function. (#13368)	2026-04-11 21:06:36 -04:00
ozbayb	ae3830a6d2	LTX2 Context Windows - Collect multimodal methods into WindowingState; Condense execution path to treat all latents as potentially multimodal	2026-04-11 11:31:04 -06:00
Jukka Seppänen	a134423890	SDPose: resize input always (#13349)	2026-04-10 11:26:55 -10:00
ozbayb	88643f3978	Fix logging of guide frame number	2026-04-07 14:11:19 -06:00
ozbayb	d1a9e2e4df	Fix whitespace	2026-04-07 13:25:31 -06:00
ozbayb	d5badc5f38	LTX2 context windows - Clean up unnecessary code	2026-04-07 13:00:38 -06:00
ozbayb	c9edd2d7c0	LTX2 context windows - Add handling for downscaled IC-Lora guide frames	2026-04-07 12:44:28 -06:00
ozbayb	f1acd5bd85	LTX2 context windows - Cleanup: Simplify window data handling, improve variable names, refactor and condense new context window methods to separate execution paths cleanly	2026-04-07 12:43:41 -06:00
huemin	b615af1c65	Add support for small flux.2 decoder (#13314)	2026-04-07 03:44:18 -04:00
comfyanonymous	40862c0776	Support Ace Step 1.5 XL model. (#13317)	2026-04-07 03:13:47 -04:00
ozbayb	3a061f4bbf	LTX2 context windows - Cleanup: Simplify IndexListContextHandler standard execute path	2026-04-06 15:13:46 -06:00
ozbayb	874690c01c	LTX2 context windows - Refactor guide logic from context_windows into LTXAV model hooks	2026-04-06 11:44:14 -06:00
ozbayb	350237618d	LTX2 context windows - Cleanup: Remove model specific code from BaseModel. Older LTXV model's guides + context_windows will need to be re-implemented but outside the scope of LTX2 changes	2026-04-06 10:10:19 -06:00
ozbayb	3660533f83	LTX2 context windows - Cleanup: latent_start value is required for context windows with guides	2026-04-06 10:10:19 -06:00
ozbayb	71712472f5	LTX2 context windows - Ensure that inplace latent images are retained properly with the retain index list	2026-04-06 10:10:19 -06:00
ozbayb	9566c18ced	LTX2 context windows - Fix crash when a window doesn't have a guide index	2026-04-06 10:10:19 -06:00
ozbayb	ef61ddfaed	Fix freenoise application for LTXAV context windows, fix audio mapping to context windows	2026-04-06 10:10:19 -06:00
ozbayb	115dbb69d1	LTX2 context windows part 3 - Generalize guide splitting to windows	2026-04-06 10:10:19 -06:00
ozbayb	941d50e777	LTX2 context windows part 2b - Calculate guide parameters in model code, refactor	2026-04-06 10:10:19 -06:00
ozbayb	56de390c25	LTX2 context windows part 2 - Guide aware processing	2026-04-06 10:10:19 -06:00
ozbayb	5bfe660b7c	Test implementation for LTX2 context windows	2026-04-06 10:10:19 -06:00
comfyanonymous	0c63b4f6e3	Remove dead code. (#13251)	2026-04-01 20:22:06 -04:00
comfyanonymous	e2ddf28d78	Fix some fp8 scaled checkpoints no longer working. (#13239)	2026-03-31 14:27:17 -07:00
rattus	8d723d2caa	Fix/tweak pinned memory accounting (#13221) ... * mm: Lower windows pin threshold Some workflows have more extranous use of shared GPU memory than is accounted for in the 5% pin headroom. Lower this for safety. * mm: Remove pin count clearing threshold. TOTAL_PINNED_MEMORY is shared between the legacy and aimdo pinning systems, however this catch-all assumes only the legacy system exists. Remove the catch-all as the PINNED_MEMORY buffer is coherent already.	2026-03-29 16:43:24 -07:00
Jukka Seppänen	a500f1edac	CORE-13 feat: Support RT-DETRv4 detection model (#12748)	2026-03-28 23:34:10 -04:00
comfyanonymous	3f77450ef1	Fix #13214 (#13216)	2026-03-28 22:35:59 -04:00
rattus	b353a7c863	Integrate RAM cache with model RAM management (#13173)	2026-03-27 21:34:16 -04:00
comfyanonymous	3a56201da5	Allow flux conditioning without a pooled output. (#13198)	2026-03-27 20:36:26 -04:00
Jukka Seppänen	b0fd65e884	fix: regression in text generate with LTXAV model (#13170)	2026-03-26 09:55:05 -07:00
comfyanonymous	2a1f402601	Make Qwen 8B work with TextGenerate node. (#13160)	2026-03-25 23:21:44 -04:00
Jukka Seppänen	404d7b9978	feat: Support Qwen3.5 text generation models (#12771)	2026-03-25 22:48:28 -04:00
Kohaku-Blueleaf	5ebb0c2e0b	FP8 bwd training (#13121)	2026-03-24 20:39:04 -04:00
Jukka Seppänen	e87858e974	feat: LTX2: Support reference audio (ID-LoRA) (#13111)	2026-03-23 18:22:24 -04:00
Talmaj	d49420b3c7	LongCat-Image edit (#13003)	2026-03-21 23:51:05 -04:00
rattus	25b6d1d629	wan: vae: Fix light/color change (#13101) ... There was an issue where the resample split was too early and dropped one of the rolling convolutions a frame early. This is most noticable as a lighting/color change between pixel frames 5->6 (latent 2->3), or as a lighting change between the first and last frame in an FLF wan flow.	2026-03-21 18:44:35 -04:00
comfyanonymous	11c15d8832	Fix fp16 intermediates giving different results. (#13100)	2026-03-21 17:53:25 -04:00
comfyanonymous	b5d32e6ad2	Fix sampling issue with fp16 intermediates. (#13099)	2026-03-21 17:47:42 -04:00
Jedrzej Kosinski	87cda1fc25	Move inline comfy.context_windows imports to top-level in model_base.py (#13083) ... The recent PR that added resize_cond_for_context_window methods to model classes used inline 'import comfy.context_windows' in each method body. This moves that import to the top-level import section, replacing 4 duplicate inline imports with a single top-level one.	2026-03-20 20:03:42 -04:00
drozbay	589228e671	Add slice_cond and per-model context window cond resizing (#12645) ... * Add slice_cond and per-model context window cond resizing * Fix cond_value.size() call in context window cond resizing * Expose additional advanced inputs for ContextWindowsManualNode Necessary for WanAnimate context windows workflow, which needs cond_retain_index_list = 0 to work properly with its reference input. ---------	2026-03-19 20:42:42 -07:00
rattus	f49856af57	ltx: vae: Fix missing init variable (#13074) ... Forgot to push this ammendment. Previous test results apply to this.	2026-03-19 22:34:58 -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
comfyanonymous	8458ae2686	Revert "fix: run text encoders on MPS GPU instead of CPU for Apple Silicon (#…" (#13070) ... This reverts commit b941913f1d.	2026-03-19 15:27:55 -04:00
Jukka Seppänen	fd0261d2bc	Reduce tiled decode peak memory (#13050)	2026-03-19 13:29:34 -04:00
rattus	ab14541ef7	memory: Add more exclusion criteria to pinned read (#13067)	2026-03-19 10:03:20 -07:00
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
comfyanonymous	f6b869d7d3	fp16 intermediates doen't work for some text enc models. (#13056)	2026-03-18 19:42:28 -04:00
comfyanonymous	56ff88f951	Fix regression. (#13053)	2026-03-18 18:35:25 -04:00
Jukka Seppänen	9fff091f35	Further Reduce LTX VAE decode peak RAM usage (#13052)	2026-03-18 18:32:26 -04:00
comfyanonymous	dcd659590f	Make more intermediate values follow the intermediate dtype. (#13051)	2026-03-18 18:14:18 -04:00
Anton Bukov	b941913f1d	fix: run text encoders on MPS GPU instead of CPU for Apple Silicon (#12809) ... On Apple Silicon, `vram_state` is set to `VRAMState.SHARED` because CPU and GPU share unified memory. However, `text_encoder_device()` only checked for `HIGH_VRAM` and `NORMAL_VRAM`, causing all text encoders to fall back to CPU on MPS devices. Adding `VRAMState.SHARED` to the condition allows non-quantized text encoders (e.g. bf16 Gemma 3 12B) to run on the MPS GPU, providing significant speedup for text encoding and prompt generation. Note: quantized models (fp4/fp8) that use float8_e4m3fn internally will still fall back to CPU via the `supports_cast()` check in `CLIP.__init__()`, since MPS does not support fp8 dtypes.	2026-03-17 21:21:32 -04:00
rattus	cad24ce262	cascade: remove dead weight init code (#13026) ... This weight init process is fully shadowed be the weight load and doesnt work in dynamic_vram were the weight allocation is deferred.	2026-03-17 20:59:10 -04:00