165 Commits

Include renames

Author	SHA1	Message	Date
comfyanonymousandGitHub	85fc35e8fa	Fix mac issue. (#12250)	2026-02-03 12:19:39 -05:00
3 people	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
comfyanonymousandGitHub	affe881354	Fix some issues with mac. (#12247)	2026-02-03 11:07:04 -05:00
comfyanonymousandGitHub	f5030e26fd	Add progress bar to ace step. (#12242)	2026-02-03 04:09:30 -05:00
comfyanonymousandGitHub	3c1a1a2df8	Basic support for the ace step 1.5 model. (#12237)	2026-02-03 00:06:18 -05:00
comfyanonymousandGitHub	dd86b15521	Enable embeddings for some qwen 3 models. (#12218)	2026-02-02 03:51:09 -05:00
rattusandGitHub	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
comfyanonymousandGitHub	873de5f37a	KV cache implementation for using llama models for text generation. (#12195)	2026-01-31 21:11:11 -05:00
comfyanonymousandGitHub	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
comfyanonymousandGitHub	09a2e67151	Support loading flux 2 klein checkpoints saved with SaveCheckpoint. (#12033)	2026-01-22 18:20:48 -05:00
Jukka SeppänenandGitHub	245f6139b6	More targeted embedding_connector loading for LTX2 text encoder (#11992) ... Reduces errors	2026-01-21 23:05:06 -05:00
comfyanonymousandGitHub	abe2ec26a6	Support the Anima model. (#12012)	2026-01-21 19:44:28 -05:00
comfyanonymousandGitHub	e755268e7b	Config for Qwen 3 0.6B model. (#11998)	2026-01-20 23:08:31 -05:00
comfyanonymousandGitHub	70c91b8248	Fix #11963 (#11982)	2026-01-19 22:32:40 -05:00
comfyanonymousandGitHub	3b832231bb	Flux2 Klein support. (#11890)	2026-01-15 10:33:15 -05:00
Jukka SeppänenandGitHub	be518db5a7	Remove extraneous clip missing warnings when loading LTX2 embeddings_connector weights (#11874)	2026-01-14 17:54:04 -05:00
comfyanonymousandGitHub	2f642d5d9b	Fix chroma fp8 te being treated as fp16. (#11795)	2026-01-10 14:40:42 -08:00
comfyanonymousandGitHub	25bc1b5b57	Add memory estimation function to ltxav text encoder. (#11716)	2026-01-07 20:11:22 -05:00
comfyanonymousandGitHub	34751fe9f9	Lower ltxv text encoder vram use. (#11713)	2026-01-07 19:12:15 -05:00
comfyanonymousandGitHub	3cd7b32f1b	Support gemma 12B with quant weights. (#11696)	2026-01-07 05:15:14 -05:00
comfyanonymousandGitHub	023cf13721	Fix lowvram issue with ltxv2 text encoder. (#11675)	2026-01-06 17:33:03 -05:00
comfyanonymousandGitHub	f2b002372b	Support the LTXV 2 model. (#11632)	2026-01-05 01:58:59 -05:00
comfyanonymousandGitHub	1bdc9a947f	Remove duplicate import of model_management (#11587)	2025-12-31 19:29:55 -05:00
comfyanonymousandGitHub	fb478f679a	Only apply gemma quant config to gemma model for newbie. (#11436)	2025-12-20 01:02:43 -05:00
woctordhoandGitHub	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
comfyanonymousandGitHub	3ab9748903	Disable prompt weights on newbie te. (#11434)	2025-12-20 00:19:47 -05:00
woctordhoandGitHub	0aa7fa464e	Implement sliding attention in Gemma3 (#11409)	2025-12-20 00:16:46 -05:00
comfyanonymousandGitHub	329480da5a	Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162)	2025-12-06 17:50:10 -08:00
Jukka SeppänenandGitHub	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
comfyanonymousandGitHub	43071e3de3	Make old scaled fp8 format use the new mixed quant ops system. (#11000)	2025-12-05 14:35:42 -05:00
comfyanonymousandGitHub	878db3a727	Implement the Ovis image model. (#11030)	2025-12-01 20:56:17 -05:00
comfyanonymousandGitHub	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
comfyanonymousandGitHub	e9aae31fa2	Z Image model. (#10892)	2025-11-25 18:41:45 -05:00
comfyanonymousandGitHub	d196a905bb	Lower vram usage for flux 2 text encoder. (#10887)	2025-11-25 14:58:39 -05:00
comfyanonymousandGitHub	dff996ca39	Fix crash. (#10885)	2025-11-25 14:30:24 -05:00
comfyanonymousandGitHub	6b573ae0cb	Flux 2 (#10879)	2025-11-25 10:50:19 -05:00
comfyanonymousandGitHub	25022e0b09	Cleanup and fix issues with text encoder quants. (#10872)	2025-11-25 01:48:53 -05:00
4 people	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
comfyanonymousandGitHub	17027f2a6a	Add a way to disable the final norm in the llama based TE models. (#10794)	2025-11-18 22:36:03 -05:00
comfyanonymousandGitHub	8aea746212	Implement gemma 3 as a text encoder. (#10241) ... Not useful yet.	2025-10-06 22:08:08 -04:00
comfyanonymousandGitHub	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
comfyanonymousandGitHub	1fee8827cb	Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. (#9986)	2025-09-22 16:49:48 -04:00
Kimbing NgandGitHub	e5e70636e7	Remove single quote pattern to avoid wrong matches (#9842)	2025-09-13 16:59:19 -04:00
comfyanonymousandGitHub	85e34643f8	Support hunyuan image 2.1 regular model. (#9792)	2025-09-10 02:05:07 -04:00
contentisandGitHub	97652d26b8	Add explicit casting in apply_rope for Qwen VL (#9759)	2025-09-08 15:08:18 -04:00
comfyanonymousandGitHub	5a8f502db5	Disable prompt weights for qwen. (#9438)	2025-08-20 01:08:11 -04:00
comfyanonymousandGitHub	dfa791eb4b	Rope fix for qwen vl. (#9435)	2025-08-19 20:47:42 -04:00
comfyanonymousandGitHub	4977f203fa	P2 of qwen edit model. (#9412) ... * P2 of qwen edit model. * Typo. * Fix normal qwen. * Fix. * Make the TextEncodeQwenImageEdit also set the ref latent. If you don't want it to set the ref latent and want to use the ReferenceLatent node with your custom latent instead just disconnect the VAE.	2025-08-18 22:38:34 -04:00
comfyanonymousandGitHub	c012400240	Initial support for qwen image model. (#9179)	2025-08-04 22:53:25 -04:00
comfyanonymousandGitHub	938d3e8216	Remove windows line endings. (#8866)	2025-07-11 02:37:51 -04:00