565 Commits

Include renames

Author	SHA1	Message	Date
John Pollock	15a500ff6b	Add SeedVR2 model and VAE support	2026-05-26 00:27:35 -05:00
Ivan ZorinandGitHub	57414dadfe	fix: cross-attention AdaLN scale, shift, sigma parameters calculation (#14097)	2026-05-25 20:07:09 -07:00
comfyanonymousandGitHub	da49b7d0b6	Remove useless annotations imports. (#14105)	2026-05-25 19:23:29 -07:00
Jedrzej KosinskiandGitHub	0a2dd86e78	MultiGPU Work Units For Accelerated Sampling (CORE-184) (#7063)	2026-05-25 18:26:40 -07:00
comfyanonymousandGitHub	08d809d128	Fix --use-flash-attention ignored when xformers installed. (#14083)	2026-05-23 17:44:28 -07:00
comfyanonymousandGitHub	f9c84c94b4	Support Stable Audio 3 model. (#14010)	2026-05-20 11:34:22 -04:00
Cezarijus KivyliusandGitHub	78b5dec6b6	fix: Hunyuan3D 2.1 batch size crashes in attention and forward pass (#13699)	2026-05-20 19:58:49 +08:00
Jukka SeppänenandGitHub	33ce449c8b	Reduce LTX2.3 peak VRAM when guide_mask is in use (CORE-166) (#13735) ... - Reduce peak VRAM by handling self_attn_mask more efficiently - Fallback to SDPA when self_attention_mask is used	2026-05-16 00:02:27 +03:00
Jukka SeppänenandGitHub	77e2ed5e01	feat: Support MoGe (CORE-168) (#13878)	2026-05-15 10:34:56 +08:00
Jukka SeppänenandGitHub	8e53f001a4	feat: Support HiDream-O1-Image (CORE-187) (#13817) ... * Initial HiDream01-image support * Cleanup nodes * Cleaner handling of empty placeholder models * Remove snap_to_predefined, prefer tooltip for the trained resolutions * Add model and block wrappers * Fix shift tooltip * Add node to work around the patch tile issue Experimental, runs multiple passes with the patch grid offset and blends with various different methods. * Qwen35 vision rotary_pos_emb cast fix * Fix embedding layout type * Some small optimizations * Cleanup, don't need this fallback * Prefix KV cache, cleanup Bit of speed, reduce redundant code * Get rid of redundant custom sampler, refactor noise scaling Our existing lcm sampler is mathematically same, just added the missing options to it instead and a node to control them. Refactored the noise scaling and fix it for the stochastic samplers, add a generic node to control the initial noise scale. * Update nodes_hidream_o1.py * Fix some cache validation cases * Keep existing sampling params * Remove redundant video vision path * Replace some numpy ops with torch * Fx RoPE index for batch size > 1 * Prefer torch preprocessing * Rename block_type to be compatible with existing patch nodes * Fixes and tweaks	2026-05-11 20:35:53 -07:00
3 people	3200f28e3a	Support Wan-Dancer (#13813) ... * initial WanDancer support * nodes_wandancer: Add list form of chunker. Create an alternate list form of the node so the chunk gens can be trivially looped by the comfy executor. * Closer match to original soxr resampling * Remove librosa node * Cleanup --------- Co-authored-by: Rattus <rattus128@gmail.com>	2026-05-09 14:02:56 -07:00
omahsandGitHub	bac6fc35fb	Fix typos (#10986)	2026-05-08 17:14:45 +08:00
Jukka SeppänenandGitHub	8dc3f3f209	Improve SAM3 large input handling (#13767)	2026-05-07 17:18:28 -07:00
TalmajandGitHub	fed8d5efa6	feat: Auto-regressive video generation (CORE-25) (#13082)	2026-05-04 21:01:22 -07:00
Jukka SeppänenandGitHub	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
rattusandGitHub	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
4 people	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 SeppänenandGitHub	084e08c6e2	Disable sageattention for SAM3 (#13529) ... Causes Nans	2026-04-23 11:14:42 -07:00
Jukka SeppänenandGitHub	749d5b4e8d	feat: SAM (segment anything) 3.1 support (CORE-34) (#13408)	2026-04-23 00:07:43 -04:00
comfyanonymousandGitHub	ad94d47221	Make the ltx audio vae more native. (#13486)	2026-04-21 11:02:42 -04:00
comfyanonymousandGitHub	3d816db07f	Some optimizations to make Ernie inference a bit faster. (#13472)	2026-04-18 23:02:29 -04:00
Jukka SeppänenandGitHub	b9dedea57d	feat: SUPIR model support (CORE-17) (#13250)	2026-04-18 23:02:01 -04:00
comfyanonymousandGitHub	cb0bbde402	Fix ernie on devices that don't support fp64. (#13414)	2026-04-14 22:54:47 -04:00
comfyanonymousandGitHub	402ff1cdb7	Fix issue with ernie image. (#13393)	2026-04-13 16:38:42 -04:00
comfyanonymousandGitHub	31283d2892	Implement Ernie Image model. (#13369)	2026-04-11 22:29:31 -04:00
comfyanonymousandGitHub	55ebd287ee	Add a supports_fp64 function. (#13368)	2026-04-11 21:06:36 -04:00
Jukka SeppänenandGitHub	a134423890	SDPose: resize input always (#13349)	2026-04-10 11:26:55 -10:00
hueminandGitHub	b615af1c65	Add support for small flux.2 decoder (#13314)	2026-04-07 03:44:18 -04:00
comfyanonymousandGitHub	40862c0776	Support Ace Step 1.5 XL model. (#13317)	2026-04-07 03:13:47 -04:00
comfyanonymousandGitHub	0c63b4f6e3	Remove dead code. (#13251)	2026-04-01 20:22:06 -04:00
Jukka SeppänenandGitHub	a500f1edac	CORE-13 feat: Support RT-DETRv4 detection model (#12748)	2026-03-28 23:34:10 -04:00
Jukka SeppänenandGitHub	e87858e974	feat: LTX2: Support reference audio (ID-LoRA) (#13111)	2026-03-23 18:22:24 -04:00
TalmajandGitHub	d49420b3c7	LongCat-Image edit (#13003)	2026-03-21 23:51:05 -04:00
rattusandGitHub	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
rattusandGitHub	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
rattusandGitHub	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
rattusandGitHub	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 SeppänenandGitHub	9fff091f35	Further Reduce LTX VAE decode peak RAM usage (#13052)	2026-03-18 18:32:26 -04:00
rattusandGitHub	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
rattusandGitHub	035414ede4	Reduce WAN VAE VRAM, Save use cases for OOM/Tiler (#13014) ... * wan: vae: encoder: Add feature cache layer that corks singles If a downsample only gives you a single frame, save it to the feature cache and return nothing to the top level. This increases the efficiency of cacheability, but also prepares support for going two by two rather than four by four on the frames. * wan: remove all concatentation with the feature cache The loopers are now responsible for ensuring that non-final frames are processes at least two-by-two, elimiating the need for this cat case. * wan: vae: recurse and chunk for 2+2 frames on decode Avoid having to clone off slices of 4 frame chunks and reduce the size of the big 6 frame convolutions down to 4. Save the VRAMs. * wan: encode frames 2x2. Reduce VRAM usage greatly by encoding frames 2 at a time rather than 4. * wan: vae: remove cloning The loopers now control the chunking such there is noever more than 2 frames, so just cache these slices directly and avoid the clone allocations completely. * wan: vae: free consumer caller tensors on recursion * wan: vae: restyle a little to match LTX	2026-03-17 17:34:39 -04:00
rattusandGitHub	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
Paulo Muggler MoreiraandGitHub	8cc746a864	fix: disable SageAttention for Hunyuan3D v2.1 DiT (#12772)	2026-03-16 22:27:27 -04:00
Jukka SeppänenandGitHub	0904cc3fe5	LTXV: Accumulate VAE decode results on intermediate_device (#12955)	2026-03-14 18:09:09 -07:00
comfyanonymousandGitHub	44f1246c89	Support flux 2 klein kv cache model: Use the FluxKVCache node. (#12905)	2026-03-12 11:30:50 -04:00
comfyanonymousandGitHub	f6274c06b4	Fix issue with batch_size > 1 on some models. (#12892)	2026-03-11 16:37:31 -04:00
comfyanonymousandGitHub	9642e4407b	Add pre attention and post input patches to qwen image model. (#12879)	2026-03-11 00:09:35 -04:00
rattusandGitHub	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
comfyanonymousandGitHub	c4fb0271cd	Add a way for nodes to add pre attn patches to flux model. (#12861)	2026-03-09 23:37:58 -04:00
comfyanonymousandGitHub	17b43c2b87	LTX audio vae novram fixes. (#12796)	2026-03-05 16:31:28 -05:00
Jukka SeppänenandGitHub	8befce5c7b	Add manual cast to LTX2 vocoder conv_transpose1d (#12795) ... * Add manual cast to LTX2 vocoder * Update vocoder.py	2026-03-05 12:37:25 -08:00