5554 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Alexander PiskunandGitHub	2687652530	fix(api-nodes): force Gemini to return uncompressed images (#12516)	2026-02-19 04:10:39 -08:00
Jukka SeppänenandGitHub	6d11cc7354	feat: Add basic text generation support with native models, initially supporting Gemma3 (#12392)	2026-02-18 20:49:43 -05:00
comfyanonymousandGitHub	f262444dd4	Add simple 3 band equalizer node for audio. (#12519)	2026-02-18 18:36:35 -05:00
Alexander PiskunandGitHub	239ddd3327	fix(api-nodes): add price badge for Rodin Gen-2 node (#12512)	2026-02-17 23:15:23 -08:00
HunterandGitHub	83dd65f23a	fix: use glob matching for Gemini image MIME types (#12511) ... gemini-3-pro-image-preview nondeterministically returns image/jpeg instead of image/png. get_image_from_response() hardcoded get_parts_by_type(response, "image/png"), silently dropping JPEG responses and falling back to torch.zeros (all-black output). Add _mime_matches() helper using fnmatch for glob-style MIME matching. Change get_image_from_response() to request "image/*" so any image format returned by the API is correctly captured.	2026-02-18 00:03:54 -05:00
4 people	8ad38d2073	BBox widget (#11594) ... * Boundingbox widget * code improve --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com> Co-authored-by: Christian Byrne <cbyrne@comfy.org>	2026-02-17 17:13:39 -08:00
3 people	6c14f129af	Bump comfyui-frontend-package to 1.39.14 (#12494) ... * Bump comfyui-frontend-package to 1.39.13 * Update requirements.txt --------- Co-authored-by: Christian Byrne <cbyrne@comfy.org>	2026-02-17 13:41:34 -08:00
rattusandGitHub	58dcc97dcf	ops: limit return of requants (#12506) ... This check was far too broad and the dtype is not a reliable indicator of wanting the requant (as QT returns the compute dtype as the dtype). So explictly plumb whether fp8mm wants the requant or not.	2026-02-17 15:32:27 -05:00
comfyanonymous	19236edfa4	ComfyUI v0.14.1 v0.14.1	2026-02-17 13:28:06 -05:00
ComfyUI WikiandGitHub	73c3f86973	chore: update workflow templates to v0.8.43 (#12507)	2026-02-17 13:25:55 -05:00
Alexander PiskunandGitHub	262abf437b	feat(api-nodes): add Recraft V4 nodes (#12502)	2026-02-17 13:25:44 -05:00
Alexander PiskunandGitHub	5284e6bf69	feat(api-nodes): add "viduq3-turbo" model and Vidu3StartEnd node; fix the price badges (#12482)	2026-02-17 10:07:14 -08:00
chaObservandGitHub	44f8598521	Fix anima LLM adapter forward when manual cast (#12504)	2026-02-17 07:56:44 -08:00
comfyanonymous	fe52843fe5	ComfyUI v0.14.0 v0.14.0	2026-02-17 00:39:54 -05:00
comfyanonymousandGitHub	c39653163d	Fix anima preprocess text embeds not using right inference dtype. (#12501)	2026-02-17 00:29:20 -05:00
comfyanonymousandGitHub	18927538a1	Implement NAG on all the models based on the Flux code. (#12500) ... Use the Normalized Attention Guidance node. Flux, Flux2, Klein, Chroma, Chroma radiance, Hunyuan Video, etc..	2026-02-16 23:30:34 -05:00
Jedrzej KosinskiandGitHub	8a6fbc2dc2	Allow control_after_generate to be type ControlAfterGenerate in v3 schema (#12187)	2026-02-16 22:20:21 -05:00
Alex ButlerandGitHub	b44fc4c589	add venv* to gitignore (#12431)	2026-02-16 22:16:19 -05:00
comfyanonymousandGitHub	4454fab7f0	Remove code to support RMSNorm on old pytorch. (#12499)	2026-02-16 20:09:24 -05:00
ComfyUI WikiandGitHub	1978f59ffd	chore: update workflow templates to v0.8.42 (#12491)	2026-02-16 17:33:43 -05:00
comfyanonymousandGitHub	88e6370527	Remove workaround for old pytorch. (#12480)	2026-02-15 20:43:53 -05:00
rattusandGitHub	c0370044cd	MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) (#12446) ... * lora: add weight shape calculations. This lets the loader know if a lora will change the shape of a weight so it can take appropriate action. * MPDynamic: force load flux img_in weight This weight is a bit special, in that the lora changes its geometry. This is rather unique, not handled by existing estimate and doesn't work for either offloading or dynamic_vram. Fix for dynamic_vram as a special case. Ideally we can fully precalculate these lora geometry changes at load time, but just get these models working first.	2026-02-15 20:30:09 -05:00
rattusandGitHub	ecd2a19661	Fix lora Extraction in offload conditions (+ dynamic_vram mode) (#12479) ... * lora_extract: Add a trange If you bite off more than your GPU can chew, this kinda just hangs. Give a rough indication of progress counting the weights in a trange. * lora_extract: Support on-the-fly patching Use the on-the-fly approach from the regular model saving logic for lora extraction too. Switch off force_cast_weights accordingly. This gets extraction working in dynamic vram while also supporting extraction on GPU offloaded.	2026-02-15 20:28:51 -05:00
3 people	2c1d06a4e3	feat(api-nodes): add Bria RMBG nodes (#12465) ... Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-02-15 17:22:30 -08:00
Alexander PiskunandGitHub	e2c71ceb00	feat(api-nodes-Tencent): add ModelTo3DUV, 3DTextureEdit, 3DParts nodes (#12428) ... * feat(api-nodes-Tencent): add ModelTo3DUV, 3DTextureEdit, 3DParts nodes * add image output to TencentModelTo3DUV node * commented out two nodes * added rate_limit check to other hunyuan3d nodes	2026-02-15 05:33:18 -08:00
Jedrzej KosinskiandGitHub	596ed68691	Node Replacement API (#12014)	2026-02-15 02:12:30 -08:00
Alexander PiskunandGitHub	ce4a1ab48d	chore(api-nodes): remove "gpt-4o" model (#12467)	2026-02-15 01:31:59 -08:00
comfyanonymousandGitHub	e1ede29d82	Remove unsafe pickle loading code that was used on pytorch older than 2.4 (#12473) ... ComfyUI hasn't started on pytorch 2.4 since last month.	2026-02-14 22:53:52 -05:00
Christian ByrneandGitHub	df1e5e8514	Update frontend package to 1.38.14 (#12469)	2026-02-14 11:01:10 -08:00
krigetaandGitHub	dc9822b7df	Add working Qwen 2512 ControlNet (Fun ControlNet) support (#12359)	2026-02-13 22:23:52 -05:00
comfyanonymousandGitHub	712efb466b	Add left padding to LTXAV text encoder. (#12456)	2026-02-13 21:56:54 -05:00
comfyanonymousandGitHub	726af73867	Fix some custom nodes. (#12455)	2026-02-13 20:21:10 -05:00
comfyanonymousandGitHub	831351a29e	Support generating attention masks for left padded text encoders. (#12454)	2026-02-13 20:15:23 -05:00
comfyanonymousandGitHub	e1add563f9	Use torch RMSNorm for flux models and refactor hunyuan video code. (#12432)	2026-02-13 15:35:13 -05:00
rattusandGitHub	8902907d7a	dynamic_vram: Training fixes (#12442)	2026-02-13 15:29:37 -05:00
comfyanonymousandGitHub	e03fe8b591	Update command to install AMD stable linux pytorch. (#12437)	2026-02-12 23:29:12 -05:00
rattusandGitHub	ae79e33345	llama: use a more efficient rope implementation (#12434) ... Get rid of the cat and unary negation and inplace add-cmul the two halves of the rope. Precompute -sin once at the start of the model rather than every transformer block. This is slightly faster on both GPU and CPU bound setups.	2026-02-12 19:56:42 -05:00
rattusandGitHub	117e214354	ModelPatcherDynamic: force load non leaf weights (#12433) ... The current behaviour of the default ModelPatcher is to .to a model only if its fully loaded, which is how random non-leaf weights get loaded in non-LowVRAM conditions. The however means they never get loaded in dynamic_vram. In the dynamic_vram case, force load them to the GPU.	2026-02-12 19:51:50 -05:00
Alexander PiskunandGitHub	4a93a62371	fix(api-nodes): add separate retry budget for 429 rate limit responses (#12421)	2026-02-12 01:38:51 -08:00
comfyanonymousandGitHub	66c18522fb	Add a tip for common error. (#12414)	2026-02-11 22:12:16 -05:00
askmyteapotandGitHub	e5ae670a40	Update ace15.py to allow min_p sampling (#12373)	2026-02-11 20:28:48 -05:00
rattusandGitHub	3fe61cedda	model_patcher: guard against none model_dtype (#12410) ... Handle the case where the _model_dtype exists but is none with the intended fallback.	2026-02-11 14:54:02 -05:00
rattusandGitHub	2a4328d639	ace15: Use dynamic_vram friendly trange (#12409) ... Factor out the ksampler trange and use it in ACE LLM to prevent the silent stall at 0 and rate distortion due to first-step model load.	2026-02-11 14:53:42 -05:00
rattusandGitHub	d297a749a2	dynamic_vram: Fix windows Aimdo crash + Fix LLM performance (#12408) ... * model_management: lazy-cache aimdo_tensor These tensors cosntructed from aimdo-allocations are CPU expensive to make on the pytorch side. Add a cache version that will be valid with signature match to fast path past whatever torch is doing. * dynamic_vram: Minimize fast path CPU work Move as much as possible inside the not resident if block and cache the formed weight and bias rather than the flat intermediates. In extreme layer weight rates this adds up.	2026-02-11 14:50:16 -05:00
3 people	2b7cc7e3b6	[API Nodes] enable Magnific Upscalers (#12179) ... * feat(api-nodes): enable Magnific Upscalers * update price badges --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-02-11 11:30:19 -08:00
5 people	4993411fd9	Dispatch desktop auto-bump when a ComfyUI release is published (#12398) ... * Dispatch desktop auto-bump on ComfyUI release publish * Fix release webhook secret checks in step conditions * Require desktop dispatch token in release webhook * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Luke Mino-Altherr <lminoaltherr@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-02-11 11:15:13 -08:00
Alexander PiskunandGitHub	2c7cef4a23	fix(api-nodes): retry on connection errors during polling instead of aborting (#12393)	2026-02-11 10:51:49 -08:00
comfyanonymousandGitHub	76a7fa96db	Make built in lora training work on anima. (#12402)	2026-02-10 22:04:32 -05:00
Kohaku-BlueleafandGitHub	cdcf4119b3	[Trainer] training with proper offloading (#12189) ... * Fix bypass dtype/device moving * Force offloading mode for training * training context var * offloading implementation in training node * fix wrong input type * Support bypass load lora model, correct adapter/offloading handling	2026-02-10 21:45:19 -05:00
3 people	dbe70b6821	Add a VideoSlice node (#12107) ... * Base TrimVideo implementation * Raise error if as_trimmed call fails * Bigger max start_time, tooltips, and formatting * Count packets unless codec has subframes * Remove incorrect nested decode * Add null check for audio streams * Support non-strict duration * Added strict_duration bool to node definition * Empty commit for approval * Fix duration * Support 5.1 audio layout on save --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2026-02-10 14:42:21 -08:00