4972 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
pythongosssss	3eb624ce6c	add comfy-angle req	2026-03-26 07:37:19 -07:00
pythongosssss	54ff5464bd	fix for mac	2026-03-24 12:10:03 -07:00
pythongosssss	333ff2e8a0	Merge remote-tracking branch 'origin/master' into pysssss/angle-glsl	2026-03-24 11:02:39 -07:00
comfyanonymous	2d4970ff67	Update frontend version to 1.42.8 (#13126)	2026-03-23 20:43:41 -04:00
Jukka Seppänen	e87858e974	feat: LTX2: Support reference audio (ID-LoRA) (#13111)	2026-03-23 18:22:24 -04:00
Dr.Lt.Data	da6edb5a4e	bump manager version to 4.1b8 (#13108)	2026-03-23 12:59:21 -04:00
pythongosssss	c821d8ee2a	add library override for windows, forcing EGL/GLESv2 -> libEGL/libGELSv2	2026-03-23 06:50:29 -07:00
pythongosssss	27b6f8a927	fix	2026-03-23 04:48:27 -07:00
comfyanonymous	6265a239f3	Add warning for users who disable dynamic vram. (#13113)	2026-03-22 18:46:18 -04:00
Talmaj	d49420b3c7	LongCat-Image edit (#13003)	2026-03-21 23:51:05 -04:00
comfyanonymous	ebf6b52e32	ComfyUI v0.18.1	2026-03-21 22:32:16 -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
comfyanonymous	a11f68dd3b	Fix canny node not working with fp16. (#13085)	2026-03-20 23:15:50 -04:00
comfyanonymous	dc719cde9c	ComfyUI version 0.18.0	2026-03-20 20:09:15 -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
comfyanonymous	45d5c83a30	Make EmptyImage node follow intermediate device/dtype. (#13079)	2026-03-20 16:08:26 -04:00
Alexander Piskun	c646d211be	feat(api-nodes): add Quiver SVG nodes (#13047)	2026-03-20 12:23:16 -07:00
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
Alexander Piskun	e4455fd43a	[API Nodes] mark seedream-3-0-t2i and seedance-1-0-lite models as deprecated (#13060) ... * chore(api-nodes): mark seedream-3-0-t2i and seedance-1-0-lite models as deprecated * fix(api-nodes): fixed old regression in the ByteDanceImageReference node --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-03-19 20:05:01 -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	6589562ae3	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 10:01:12 -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
pythongosssss	9ad848bd59	unused	2026-03-19 08:08:21 -07:00
pythongosssss	efe6439ad0	update to use comfy_angle lib	2026-03-19 08:08:07 -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
Alexander Brown	b67ed2a45f	Update comfyui-frontend-package version to 1.41.21 (#13035)	2026-03-18 16:36:39 -04:00
Alexander Piskun	06957022d4	fix(api-nodes): add support for "thought_image" in Nano Banana 2 and corrected price badges (#13038)	2026-03-18 10:21:58 -07:00
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
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
Dr.Lt.Data	8b9d039f26	bump manager version to 4.1b6 (#13022)	2026-03-17 18:17:03 -04:00
rattus	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
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
Christian Byrne	ed7c2c6579	Mark weight_dtype as advanced input in Load Diffusion Model node (#12769) ... Mark the weight_dtype parameter in UNETLoader (Load Diffusion Model) as an advanced input to reduce UI complexity for new users. The parameter is now hidden behind an expandable Advanced section, matching the pattern used for other advanced inputs like device, tile_size, and overlap. Amp-Thread-ID: https://ampcode.com/threads/T-019cbaf1-d3c0-718e-a325-318baba86dec	2026-03-17 07:24:00 -07:00
pythongosssss	8d76bb94fd	angle	2026-03-17 02:51:47 -07:00
ComfyUI Wiki	379fbd1a82	chore: update workflow templates to v0.9.26 (#13012)	2026-03-16 21:53:18 -07:00
Paulo Muggler Moreira	8cc746a864	fix: disable SageAttention for Hunyuan3D v2.1 DiT (#12772)	2026-03-16 22:27:27 -04:00
Christian Byrne	9a870b5102	fix: atomic writes for userdata to prevent data loss on crash (#12987) ... Write to a temp file in the same directory then os.replace() onto the target path. If the process crashes mid-write, the original file is left intact instead of being truncated to zero bytes. Fixes #11298	2026-03-16 21:56:35 -04:00
comfyanonymous	ca17fc8355	Fix potential issue. (#13009)	2026-03-16 21:38:40 -04:00
Kohaku-Blueleaf	20561aa919	[Trainer] FP4, 8, 16 training by native dtype support and quant linear autograd function (#12681)	2026-03-16 21:31:50 -04:00