comfyanonymous and GitHub
d69d30819b
Don't run TE on cpu when dynamic vram enabled. ( #12815 )
2026-03-06 19:11:16 -05:00
comfyanonymous and GitHub
17b43c2b87
LTX audio vae novram fixes. ( #12796 )
2026-03-05 16:31:28 -05:00
comfyanonymous and GitHub
1c3b651c0a
Refactor. ( #12794 )
2026-03-05 13:35:56 -05:00
comfyanonymous and GitHub
4941671b5a
Fix cuda getting initialized in cpu mode. ( #12779 )
2026-03-05 02:39:51 -05:00
comfyanonymous and GitHub
f2ee7f2d36
Fix cublas ops on dynamic vram. ( #12776 )
2026-03-05 01:21:55 -05:00
comfyanonymous and GitHub
43c64b6308
Support the LTXAV 2.3 model. ( #12773 )
2026-03-04 20:06:20 -05:00
comfyanonymous and GitHub
ac4a943ff3
Initial load device should be cpu when using dynamic vram. ( #12766 )
2026-03-04 16:33:14 -05:00
comfyanonymous and GitHub
f719a9d928
Adjust memory usage factor of zeta model. ( #12746 )
2026-03-03 17:35:22 -05:00
comfyanonymous and GitHub
57dd6c1aad
Support loading zeta chroma weights properly. ( #12734 )
2026-03-02 18:54:18 -05:00
comfyanonymous and GitHub
602f6bd82c
Make --disable-smart-memory disable dynamic vram. ( #12722 )
2026-03-01 15:28:39 -05:00
comfyanonymous and GitHub
1080bd442a
Disable dynamic vram on wsl. ( #12706 )
2026-02-28 22:23:28 -05:00
comfyanonymous and GitHub
17106cb124
Move parsing of requirements logic to function. ( #12701 )
2026-02-28 22:21:32 -05:00
comfyanonymous and GitHub
9d0e114ee3
PyOpenGL-accelerate is not necessary. ( #12692 )
2026-02-27 23:34:58 -05:00
comfyanonymous and GitHub
94f1a1cc9d
Limit overlap in image tile and combine nodes to prevent issues. ( #12688 )
2026-02-27 20:16:24 -05:00
comfyanonymous and GitHub
3811780e4f
Portable with cu128 isn't useful anymore. ( #12666 )
...
Users should either use the cu126 one or the regular one (cu130 at the moment)
The cu128 portable is still included in the latest github release but I will stop including it as soon as it becomes slightly annoying to deal with. This might happen as soon as next week.
2026-02-26 17:12:29 -05:00
comfyanonymous and GitHub
8a4d85c708
Cleanups to the last PR. ( #12646 )
2026-02-26 01:30:31 -05:00
comfyanonymous and GitHub
7253531670
Fix ltxav te mem estimation. ( #12643 )
2026-02-25 23:13:47 -05:00
comfyanonymous and GitHub
e14b04478c
Fix LTXAV text enc min length. ( #12640 )
...
Should have been 1024 instead of 512
2026-02-25 22:36:02 -05:00
comfyanonymous and GitHub
599f9c5010
Don't crash right away if op is uninitialized. ( #12615 )
2026-02-24 12:28:25 -05:00
comfyanonymous and GitHub
84aba95e03
Temporality unbreak some LTXAV workflows to give people time to migrate. ( #12605 )
2026-02-24 00:50:03 -05:00
comfyanonymous and GitHub
9b1c63eb69
Add SplitImageToTileList and ImageMergeTileList nodes. ( #12599 )
...
With these you can split an image into tiles, do operations and then combine it back to a single image.
2026-02-23 21:01:17 -05:00
comfyanonymous and GitHub
caa43d2395
Fix issue loading fp8 ltxav checkpoints. ( #12582 )
2026-02-22 16:00:02 -05:00
comfyanonymous and GitHub
07ca6852e8
Fix dtype issue in embeddings connector. ( #12570 )
2026-02-22 03:18:20 -05:00
comfyanonymous and GitHub
f266b8d352
Move LTXAV av embedding connectors to diffusion model. ( #12569 )
2026-02-21 22:29:58 -05:00
comfyanonymous and GitHub
64953bda0a
Update nightly installation command for ROCm ( #12547 )
2026-02-20 21:32:05 -05:00
comfyanonymous and GitHub
5f2117528a
Force min length 1 when tokenizing for text generation. ( #12538 )
2026-02-19 22:57:44 -05:00
comfyanonymous and GitHub
0301ccf745
Small cleanup and try to get qwen 3 work with the text gen. ( #12537 )
2026-02-19 22:42:28 -05:00
comfyanonymous and GitHub
f262444dd4
Add simple 3 band equalizer node for audio. ( #12519 )
2026-02-18 18:36:35 -05:00
comfyanonymous and GitHub
c39653163d
Fix anima preprocess text embeds not using right inference dtype. ( #12501 )
2026-02-17 00:29:20 -05:00
comfyanonymous and GitHub
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
comfyanonymous and GitHub
4454fab7f0
Remove code to support RMSNorm on old pytorch. ( #12499 )
2026-02-16 20:09:24 -05:00
comfyanonymous and GitHub
88e6370527
Remove workaround for old pytorch. ( #12480 )
2026-02-15 20:43:53 -05:00
comfyanonymous and GitHub
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
comfyanonymous and GitHub
712efb466b
Add left padding to LTXAV text encoder. ( #12456 )
2026-02-13 21:56:54 -05:00
comfyanonymous and GitHub
726af73867
Fix some custom nodes. ( #12455 )
2026-02-13 20:21:10 -05:00
comfyanonymous and GitHub
831351a29e
Support generating attention masks for left padded text encoders. ( #12454 )
2026-02-13 20:15:23 -05:00
comfyanonymous and GitHub
e1add563f9
Use torch RMSNorm for flux models and refactor hunyuan video code. ( #12432 )
2026-02-13 15:35:13 -05:00
comfyanonymous and GitHub
e03fe8b591
Update command to install AMD stable linux pytorch. ( #12437 )
2026-02-12 23:29:12 -05:00
comfyanonymous and GitHub
66c18522fb
Add a tip for common error. ( #12414 )
2026-02-11 22:12:16 -05:00
comfyanonymous and GitHub
76a7fa96db
Make built in lora training work on anima. ( #12402 )
2026-02-10 22:04:32 -05:00
comfyanonymous and GitHub
a4be04c5d7
Ace step prompts match now. ( #12376 )
2026-02-09 19:45:56 -05:00
comfyanonymous and GitHub
a0302cc6a8
Make tonemap latent work on any dim latents. ( #12363 )
2026-02-08 21:16:40 -05:00
comfyanonymous and GitHub
f350a84261
Disable prompt weights for ltxv2. ( #12354 )
2026-02-07 19:16:28 -05:00
comfyanonymous and GitHub
17e7df43d1
Pad ace step 1.5 ref audio if not long enough. ( #12341 )
2026-02-07 00:02:11 -05:00
comfyanonymous and GitHub
039955c527
Some fixes to previous pr. ( #12339 )
2026-02-06 20:14:52 -05:00
comfyanonymous and GitHub
204e65b8dc
Fix bug with last pr ( #12338 )
2026-02-06 19:48:20 -05:00
comfyanonymous and GitHub
eba6c940fd
Make ace step 1.5 base model work properly with default workflow. ( #12337 )
2026-02-06 19:14:56 -05:00
comfyanonymous and GitHub
c2d7f07dbf
Fix issue when using disable_unet_model_creation ( #12315 )
2026-02-05 19:24:09 -05:00
comfyanonymous and GitHub
458292fef0
Fix some lowvram stuff with ace step 1.5 ( #12312 )
2026-02-05 19:15:04 -05:00
comfyanonymous and GitHub
6555dc65b8
Make ace step 1.5 work without the llm. ( #12311 )
2026-02-05 16:43:45 -05:00
comfyanonymous and GitHub
35183543e0
Add VAE tiled decode node for audio. ( #12299 )
2026-02-05 01:12:04 -05:00
comfyanonymous and GitHub
a50c32d63f
Disable sage attention on ace step 1.5 ( #12297 )
2026-02-04 22:15:30 -05:00
comfyanonymous and GitHub
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 and GitHub
c8fcbd66ee
Try to fix ace text encoder slowness on some configs. ( #12290 )
2026-02-04 19:37:05 -05:00
comfyanonymous and GitHub
26dd7eb421
Fix ace step nan issue on some hardware/pytorch configs. ( #12289 )
2026-02-04 18:25:06 -05:00
comfyanonymous and GitHub
a31681564d
Fix crash with ace step 1.5 ( #12264 )
2026-02-04 00:03:21 -05:00
comfyanonymous and GitHub
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 and GitHub
b8315e66cb
Fix tiled vae for ace step 1.5 ( #12253 )
2026-02-03 14:40:45 -05:00
comfyanonymous and GitHub
ab1050bec3
Support ace step 1.5 base model loras. ( #12252 )
2026-02-03 13:54:23 -05:00
comfyanonymous and GitHub
85fc35e8fa
Fix mac issue. ( #12250 )
2026-02-03 12:19:39 -05:00
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 and GitHub
affe881354
Fix some issues with mac. ( #12247 )
2026-02-03 11:07:04 -05:00
comfyanonymous and GitHub
f5030e26fd
Add progress bar to ace step. ( #12242 )
2026-02-03 04:09:30 -05:00
comfyanonymous and GitHub
3c1a1a2df8
Basic support for the ace step 1.5 model. ( #12237 )
2026-02-03 00:06:18 -05:00
comfyanonymous and GitHub
c05a08ae66
Add back function. ( #12234 )
2026-02-02 19:52:07 -05:00
comfyanonymous and GitHub
dd86b15521
Enable embeddings for some qwen 3 models. ( #12218 )
2026-02-02 03:51:09 -05:00
comfyanonymous and GitHub
021ba20719
Fix issue with parameters on root model object. ( #12216 )
2026-02-01 20:12:52 -05:00
comfyanonymous and GitHub
667a1b8878
Fix some custom nodes breaking. ( #12203 )
2026-02-01 01:55:18 -05:00
comfyanonymous and GitHub
873de5f37a
KV cache implementation for using llama models for text generation. ( #12195 )
2026-01-31 21:11:11 -05:00
comfyanonymous and GitHub
b8f848bfe3
Fix model not working with any res. ( #12186 )
2026-01-31 00:12:48 -05:00
comfyanonymous and GitHub
4064062e7d
Update python patch version in dep workflow. ( #12184 )
2026-01-30 20:20:06 -05:00
comfyanonymous and GitHub
bbe2c13a70
Make empty hunyuan latent 1.0 work with the 1.5 model. ( #12171 )
2026-01-29 23:52:22 -05:00
comfyanonymous and GitHub
c9b633d84f
Add missing spacial downscale ratios. ( #12146 )
2026-01-28 20:52:51 -05:00
comfyanonymous and GitHub
4f5bd39b1c
Update Python 3.14 compatibility notes in README ( #12127 )
2026-01-27 19:58:48 -05:00
comfyanonymous and GitHub
2db3b0ff90
Update amd portable for rocm 7.2 ( #12101 )
...
* Update amd portable for rocm 7.2
* Update Python patch version in release workflow
2026-01-26 19:49:31 -05:00
comfyanonymous and GitHub
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 and GitHub
7ee77ff038
Add name to LoraLoaderModelOnly. ( #12078 )
2026-01-25 21:01:55 -05:00
comfyanonymous and GitHub
26c5bbb875
Move nodes from previous PR into their own file. ( #12066 )
2026-01-24 23:02:32 -05:00
comfyanonymous and GitHub
635406e283
Only enable fp16 on z image models that actually support it. ( #12065 )
2026-01-24 22:32:28 -05:00
comfyanonymous and GitHub
aef4e13588
Make empty latent node work with other models. ( #12062 )
2026-01-24 19:23:20 -05:00
comfyanonymous and GitHub
9cf299a9f9
Make regular empty latent node work properly on flux 2 variants. ( #12050 )
2026-01-23 19:50:48 -05:00
comfyanonymous and GitHub
f443b9f2ca
Revert "feat: Improve ResizeImageMaskNode UX with tooltips and search aliases…" ( #12038 )
...
This reverts commit 4e3038114a
2026-01-22 23:02:37 -05:00
comfyanonymous and GitHub
09a2e67151
Support loading flux 2 klein checkpoints saved with SaveCheckpoint. ( #12033 )
2026-01-22 18:20:48 -05:00
comfyanonymous and GitHub
abe2ec26a6
Support the Anima model. ( #12012 )
2026-01-21 19:44:28 -05:00
comfyanonymous and GitHub
e755268e7b
Config for Qwen 3 0.6B model. ( #11998 )
2026-01-20 23:08:31 -05:00
comfyanonymous and GitHub
8ccc0c94fa
Make omni stuff work on regular z image for easier testing. ( #11985 )
2026-01-20 00:32:00 -05:00
comfyanonymous and GitHub
2108167f9f
Support zimage omni base model. ( #11979 )
2026-01-19 23:17:38 -05:00
comfyanonymous and GitHub
70c91b8248
Fix #11963 ( #11982 )
2026-01-19 22:32:40 -05:00
comfyanonymous and GitHub
e0eacb0688
Simpler way to implement the #11980 loras. ( #11981 )
2026-01-19 22:00:36 -05:00
comfyanonymous and GitHub
1a72bf2046
Readme update. ( #11957 )
2026-01-18 19:53:43 -08:00
comfyanonymous and GitHub
190c4416cc
Bump comfy-kitchen dependency to version 0.2.7 ( #11941 )
2026-01-17 21:20:35 -05:00
comfyanonymous and GitHub
7ac999bf30
Add image sizes to clip vision outputs. ( #11923 )
2026-01-16 23:02:28 -05:00
comfyanonymous and GitHub
4c816d5c69
Adjust memory usage factor calculation for flux2 klein. ( #11900 )
2026-01-15 20:06:40 -05:00
comfyanonymous and GitHub
3b832231bb
Flux2 Klein support. ( #11890 )
2026-01-15 10:33:15 -05:00
comfyanonymous and GitHub
d150440466
Fix VAELoader ( #11880 )
2026-01-14 10:54:50 -08:00
comfyanonymous and GitHub
6165c38cb5
Optimize nvfp4 lora applying. ( #11866 )
...
This changes results a bit but it also speeds up things a lot.
2026-01-14 00:49:38 -05:00
comfyanonymous and GitHub
eff2b9d412
Optimize nvfp4 lora applying. ( #11856 )
2026-01-13 19:37:19 -05:00
comfyanonymous and GitHub
15b312de7a
Optimize nvfp4 lora applying. ( #11854 )
2026-01-13 19:23:58 -05:00
comfyanonymous and GitHub
1dcbd9efaf
Bump ltxav mem estimation a bit. ( #11842 )
2026-01-13 01:42:07 -05:00
comfyanonymous and GitHub
117e7a5853
Refactor to try to lower mem usage. ( #11840 )
2026-01-12 21:01:52 -08:00
comfyanonymousandGitHub
