119 Commits

Author	SHA1	Message	Date
comfyanonymous	6125b80979	Add llm sampling options and make reference audio work on ace step 1.5 (#12295)	2026-02-04 21:29:22 -05:00
comfyanonymous	26dd7eb421	Fix ace step nan issue on some hardware/pytorch configs. (#12289)	2026-02-04 18:25:06 -05:00
comfyanonymous	a31681564d	Fix crash with ace step 1.5 (#12264)	2026-02-04 00:03:21 -05:00
comfyanonymous	fe2511468d	Support the 4B ace step 1.5 lm model. (#12257) ... Can be used as an alternative to the 1.7B	2026-02-03 19:01:38 -05:00
comfyanonymous	85fc35e8fa	Fix mac issue. (#12250)	2026-02-03 12:19:39 -05:00
comfyanonymous	223364743c	llama: cast logits as a comfy-weight (#12248) ... This is using a different layers weight with .to(). Change it to use the ops caster if the original layer is a comfy weight so that it picks up dynamic_vram and async_offload functionality in full. Co-authored-by: Rattus <rattus128@gmail.com>	2026-02-03 11:31:36 -05:00
comfyanonymous	affe881354	Fix some issues with mac. (#12247)	2026-02-03 11:07:04 -05:00
comfyanonymous	f5030e26fd	Add progress bar to ace step. (#12242)	2026-02-03 04:09:30 -05:00
comfyanonymous	3c1a1a2df8	Basic support for the ace step 1.5 model. (#12237)	2026-02-03 00:06:18 -05:00
comfyanonymous	dd86b15521	Enable embeddings for some qwen 3 models. (#12218)	2026-02-02 03:51:09 -05:00
rattus	f8acd9c402	Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845)	2026-02-01 01:01:11 -05:00
comfyanonymous	873de5f37a	KV cache implementation for using llama models for text generation. (#12195)	2026-01-31 21:11:11 -05:00
comfyanonymous	2129e7d278	Fix mistral 3 tokenizer code failing on latest transformers version and other breakage. (#12095) ... * Fix mistral 3 tokenizer code failing on latest transformers version. * Add requests to the requirements	2026-01-26 11:39:00 -05:00
comfyanonymous	09a2e67151	Support loading flux 2 klein checkpoints saved with SaveCheckpoint. (#12033)	2026-01-22 18:20:48 -05:00
Jukka Seppänen	245f6139b6	More targeted embedding_connector loading for LTX2 text encoder (#11992) ... Reduces errors	2026-01-21 23:05:06 -05:00
comfyanonymous	abe2ec26a6	Support the Anima model. (#12012)	2026-01-21 19:44:28 -05:00
comfyanonymous	e755268e7b	Config for Qwen 3 0.6B model. (#11998)	2026-01-20 23:08:31 -05:00
comfyanonymous	70c91b8248	Fix #11963 (#11982)	2026-01-19 22:32:40 -05:00
comfyanonymous	3b832231bb	Flux2 Klein support. (#11890)	2026-01-15 10:33:15 -05:00
Jukka Seppänen	be518db5a7	Remove extraneous clip missing warnings when loading LTX2 embeddings_connector weights (#11874)	2026-01-14 17:54:04 -05:00
comfyanonymous	2f642d5d9b	Fix chroma fp8 te being treated as fp16. (#11795)	2026-01-10 14:40:42 -08:00
comfyanonymous	25bc1b5b57	Add memory estimation function to ltxav text encoder. (#11716)	2026-01-07 20:11:22 -05:00
comfyanonymous	34751fe9f9	Lower ltxv text encoder vram use. (#11713)	2026-01-07 19:12:15 -05:00
comfyanonymous	3cd7b32f1b	Support gemma 12B with quant weights. (#11696)	2026-01-07 05:15:14 -05:00
comfyanonymous	023cf13721	Fix lowvram issue with ltxv2 text encoder. (#11675)	2026-01-06 17:33:03 -05:00
comfyanonymous	f2b002372b	Support the LTXV 2 model. (#11632)	2026-01-05 01:58:59 -05:00
comfyanonymous	1bdc9a947f	Remove duplicate import of model_management (#11587)	2025-12-31 19:29:55 -05:00
comfyanonymous	fb478f679a	Only apply gemma quant config to gemma model for newbie. (#11436)	2025-12-20 01:02:43 -05:00
woctordho	4c432c11ed	Implement Jina CLIP v2 and NewBie dual CLIP (#11415) ... * Implement Jina CLIP v2 * Support quantized Gemma in NewBie dual CLIP	2025-12-20 00:57:22 -05:00
comfyanonymous	3ab9748903	Disable prompt weights on newbie te. (#11434)	2025-12-20 00:19:47 -05:00
woctordho	0aa7fa464e	Implement sliding attention in Gemma3 (#11409)	2025-12-20 00:16:46 -05:00
comfyanonymous	329480da5a	Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162)	2025-12-06 17:50:10 -08:00
Jukka Seppänen	fd109325db	Kandinsky5 model support (#10988) ... * Add Kandinsky5 model support lite and pro T2V tested to work * Update kandinsky5.py * Fix fp8 * Fix fp8_scaled text encoder * Add transformer_options for attention * Code cleanup, optimizations, use fp32 for all layers originally at fp32 * ImageToVideo -node * Fix I2V, add necessary latent post process nodes * Support text to image model * Support block replace patches (SLG mostly) * Support official LoRAs * Don't scale RoPE for lite model as that just doesn't work... * Update supported_models.py * Rever RoPE scaling to simpler one * Fix typo * Handle latent dim difference for image model in the VAE instead * Add node to use different prompts for clip_l and qwen25_7b * Reduce peak VRAM usage a bit * Further reduce peak VRAM consumption by chunking ffn * Update chunking * Update memory_usage_factor * Code cleanup, don't force the fp32 layers as it has minimal effect * Allow for stronger changes with first frames normalization Default values are too weak for any meaningful changes, these should probably be exposed as advanced node options when that's available. * Add image model's own chat template, remove unused image2video template * Remove hard error in ReplaceVideoLatentFrames -node * Update kandinsky5.py * Update supported_models.py * Fix typos in prompt template They were now fixed in the original repository as well * Update ReplaceVideoLatentFrames Add tooltips Make source optional Better handle negative index * Rename NormalizeVideoLatentFrames -node For bit better clarity what it does * Fix NormalizeVideoLatentStart node out on non-op	2025-12-05 22:20:22 -05:00
comfyanonymous	43071e3de3	Make old scaled fp8 format use the new mixed quant ops system. (#11000)	2025-12-05 14:35:42 -05:00
comfyanonymous	878db3a727	Implement the Ovis image model. (#11030)	2025-12-01 20:56:17 -05:00
comfyanonymous	2640acb31c	Update qwen tokenizer to add qwen 3 tokens. (#11029) ... Doesn't actually change anything for current workflows because none of the current models have a template with the think tokens.	2025-12-01 17:13:48 -05:00
comfyanonymous	e9aae31fa2	Z Image model. (#10892)	2025-11-25 18:41:45 -05:00
comfyanonymous	d196a905bb	Lower vram usage for flux 2 text encoder. (#10887)	2025-11-25 14:58:39 -05:00
comfyanonymous	dff996ca39	Fix crash. (#10885)	2025-11-25 14:30:24 -05:00
comfyanonymous	6b573ae0cb	Flux 2 (#10879)	2025-11-25 10:50:19 -05:00
comfyanonymous	25022e0b09	Cleanup and fix issues with text encoder quants. (#10872)	2025-11-25 01:48:53 -05:00
comfyanonymous	943b3b615d	HunyuanVideo 1.5 (#10819) ... * init * update * Update model.py * Update model.py * remove print * Fix text encoding * Prevent empty negative prompt Really doesn't work otherwise * fp16 works * I2V * Update model_base.py * Update nodes_hunyuan.py * Better latent rgb factors * Use the correct sigclip output... * Support HunyuanVideo1.5 SR model * whitespaces... * Proper latent channel count * SR model fixes This also still needs timesteps scheduling based on the noise scale, can be used with two samplers too already * vae_refiner: roll the convolution through temporal Work in progress. Roll the convolution through time using 2-latent-frame chunks and a FIFO queue for the convolution seams. * Support HunyuanVideo15 latent resampler * fix * Some cleanup Co-Authored-By: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com> * Proper hyvid15 I2V channels Co-Authored-By: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com> * Fix TokenRefiner for fp16 Otherwise x.sum has infs, just in case only casting if input is fp16, I don't know if necessary. * Bugfix for the HunyuanVideo15 SR model * vae_refiner: roll the convolution through temporal II Roll the convolution through time using 2-latent-frame chunks and a FIFO queue for the convolution seams. Added support for encoder, lowered to 1 latent frame to save more VRAM, made work for Hunyuan Image 3.0 (as code shared). Fixed names, cleaned up code. * Allow any number of input frames in VAE. * Better VAE encode mem estimation. * Lowvram fix. * Fix hunyuan image 2.1 refiner. * Fix mistake. * Name changes. * Rename. * Whitespace. * Fix. * Fix. --------- Co-authored-by: kijai <40791699+kijai@users.noreply.github.com> Co-authored-by: Rattus <rattus128@gmail.com>	2025-11-20 22:44:43 -05:00
comfyanonymous	17027f2a6a	Add a way to disable the final norm in the llama based TE models. (#10794)	2025-11-18 22:36:03 -05:00
comfyanonymous	8aea746212	Implement gemma 3 as a text encoder. (#10241) ... Not useful yet.	2025-10-06 22:08:08 -04:00
comfyanonymous	1e098d6132	Don't add template to qwen2.5vl when template is in prompt. (#10043) ... Make the hunyuan image refiner template_end 36.	2025-09-26 18:34:17 -04:00
comfyanonymous	1fee8827cb	Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. (#9986)	2025-09-22 16:49:48 -04:00
Kimbing Ng	e5e70636e7	Remove single quote pattern to avoid wrong matches (#9842)	2025-09-13 16:59:19 -04:00
comfyanonymous	85e34643f8	Support hunyuan image 2.1 regular model. (#9792)	2025-09-10 02:05:07 -04:00
contentis	97652d26b8	Add explicit casting in apply_rope for Qwen VL (#9759)	2025-09-08 15:08:18 -04:00
comfyanonymous	5a8f502db5	Disable prompt weights for qwen. (#9438)	2025-08-20 01:08:11 -04:00