613 Commits

Author	SHA1	Message	Date
Yousef R. Gamaleldin	c05bff7ab8	Merge branch 'master' into trellis2	2026-05-08 14:50:49 +03:00
omahs	bac6fc35fb	Fix typos (#10986)	2026-05-08 17:14:45 +08:00
Jukka Seppänen	8dc3f3f209	Improve SAM3 large input handling (#13767)	2026-05-07 17:18:28 -07:00
Yousef Rafat	ca150ba567	simplify and optimize model.forward	2026-05-07 18:47:03 +03:00
Yousef R. Gamaleldin	2f526f202b	Merge branch 'master' into trellis2	2026-05-05 23:20:05 +03:00
Talmaj	fed8d5efa6	feat: Auto-regressive video generation (CORE-25) (#13082)	2026-05-04 21:01:22 -07:00
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
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	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
comfyanonymous	ad94d47221	Make the ltx audio vae more native. (#13486)	2026-04-21 11:02:42 -04:00
John Pollock	149af779ed	Harden Trellis sparse latent seeding	2026-04-20 16:05:10 -05:00
John Pollock	f309cc1889	Harden Trellis sparse metadata validation	2026-04-20 14:46:23 -05:00
John Pollock	e95be49e69	Fix Trellis seeded sparse batch semantics	2026-04-20 14:29:07 -05:00
John Pollock	032943a065	Fix Trellis PR review regressions	2026-04-20 12:15:49 -05:00
John Pollock	eaf7d708b0	Fix Trellis2 batched shape and texture semantics	2026-04-20 11:06:04 -05:00
John Pollock	e11bd314be	Trellis2: guard structure shape_rule pruning to CFG batches	2026-04-19 21:38:45 -05:00
John Pollock	65430280ff	Trellis2: slice cond half of x symmetrically under shape_rule pruning	2026-04-19 21:26:48 -05:00
John Pollock	233f234316	clarify: issue 86 latent-to-pixel resolution mapping	2026-04-19 19:20:14 -05:00
John Pollock	432493c19c	fix: issue 86 1024 conditioning gate	2026-04-19 18:23:17 -05:00
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
comfyanonymous	cb0bbde402	Fix ernie on devices that don't support fp64. (#13414)	2026-04-14 22:54:47 -04:00
comfyanonymous	402ff1cdb7	Fix issue with ernie image. (#13393)	2026-04-13 16:38:42 -04:00
Yousef R. Gamaleldin	18dd46b2eb	Merge branch 'master' into trellis2	2026-04-12 20:19:33 +02:00
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
Jukka Seppänen	a134423890	SDPose: resize input always (#13349)	2026-04-10 11:26:55 -10:00
Yousef Rafat	aab8ab6638	comfy ops + color support in postprocess	2026-04-10 16:12:23 +02:00
Yousef Rafat	986b8201da	structure generation works	2026-04-10 14:24:07 +02:00
Yousef Rafat	064d1b7495	removed unnecessary vae float32 upcast	2026-04-08 19:08:26 +02:00
Yousef Rafat	a7117da8de	fix for conditioning	2026-04-07 23:02:33 +02:00
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
Yousef Rafat	572dff904a	texture generation works	2026-04-03 01:22:38 +02:00
comfyanonymous	0c63b4f6e3	Remove dead code. (#13251)	2026-04-01 20:22:06 -04:00
Jukka Seppänen	a500f1edac	CORE-13 feat: Support RT-DETRv4 detection model (#12748)	2026-03-28 23:34:10 -04:00
Yousef Rafat	4ee664d99c	..	2026-03-27 20:52:23 +02:00
Yousef Rafat	7ee735fb2b	fixed color addition	2026-03-25 23:51:54 +02:00
Yousef Rafat	88cfccd83d	work on txt gen	2026-03-24 02:44:03 +02:00
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
Yousef Rafat	89c041002e	shape working	2026-03-20 18:37:11 +02:00
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
Yousef Rafat	6664ab5c1c	.	2026-03-20 02:36:01 +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
Jukka Seppänen	9fff091f35	Further Reduce LTX VAE decode peak RAM usage (#13052)	2026-03-18 18:32:26 -04:00