andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,402 Commits 1 Branch 0 Tags
ba6080bbab070934ea6e870c5fc30dbf702eb445
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
comfyanonymousandGitHub 16d85ea133 Better handle torch being imported by prestartup nodes. (#11383) 2025-12-17 19:43:18 -05:00
comfyanonymousandGitHub ffdd53b327 Check state dict key to auto enable the index_timestep_zero ref method. (#11362) 2025-12-16 17:03:17 -05:00
comfyanonymousandGitHub bc606d7d64 Add a way to set the default ref method in the qwen image code. (#11349) 2025-12-16 01:26:55 -05:00
comfyanonymousandGitHub 645ee1881e Inpainting for z image fun control. Use the ZImageFunControlnet node. (#11346) 
image -> control image ex: pose
inpaint_image -> image for inpainting
mask -> inpaint mask
 2025-12-15 23:38:12 -05:00
comfyanonymousandGitHub 683569de55 Only enable fp16 on ZImage on newer pytorch. (#11344) 2025-12-15 22:33:27 -05:00
comfyanonymousandGitHub 41bcf0619d Add code to detect if a z image fun controlnet is broken or not. (#11341) 2025-12-15 20:51:06 -05:00
comfyanonymousandGitHub 70541d4e77 Support the new qwen edit 2511 reference method. (#11340) 
index_timestep_zero can be selected in the
FluxKontextMultiReferenceLatentMethod now with the display name set to the
more generic "Edit Model Reference Method" node.
 2025-12-15 19:20:34 -05:00
comfyanonymousandGitHub 5cb1e0c9a0 Disable guards on transformer_options when torch.compile (#11317) 2025-12-15 16:49:29 -05:00
comfyanonymousandGitHub 5ac3b26a7d Update warning for old pytorch version. (#11319) 
Versions below 2.4 are no longer supported. We will not break support on purpose but will not fix it if we do.
 2025-12-14 04:02:50 -05:00
comfyanonymousandGitHub 971cefe7d4 Fix pytorch warnings. (#11314) 2025-12-13 18:45:23 -05:00
comfyanonymousandGitHub da2bfb5b0a Basic implementation of z image fun control union 2.0 (#11304) 
The inpaint part is currently missing and will be implemented later.

I think they messed up this model pretty bad. They added some
control_noise_refiner blocks but don't actually use them. There is a typo
in their code so instead of doing control_noise_refiner -> control_layers
it runs the whole control_layers twice.

Unfortunately they trained with this typo so the model works but is kind
of slow and would probably perform a lot better if they corrected their
code and trained it again.
 2025-12-13 01:39:11 -05:00
comfyanonymousandGitHub c5a47a1692 Fix bias dtype issue in mixed ops. (#11293) 2025-12-12 11:49:35 -05:00
comfyanonymousandGitHub 5495589db3 Respect the dtype the op was initialized in for non quant mixed op. (#11282) 2025-12-11 23:32:27 -05:00
comfyanonymousandGitHub 338d9ae3bb Make portable updater work with repos in unmerged state. (#11281) 2025-12-11 18:56:33 -05:00
comfyanonymousandGitHub eeb020b9b7 Better chroma radiance and other models vram estimation. (#11278) 2025-12-11 17:33:09 -05:00
comfyanonymousandGitHub ae65433a60 This only works on radiance. (#11277) 2025-12-11 17:15:00 -05:00
comfyanonymousandGitHub fdebe18296 Fix regular chroma radiance (#11276) 2025-12-11 17:09:35 -05:00
comfyanonymousandGitHub f8321eb57b Adjust memory usage factor. (#11257) 2025-12-11 01:30:31 -05:00
comfyanonymousandGitHub 17c92a9f28 Tweak Z Image memory estimation. (#11254) 2025-12-10 19:59:48 -05:00
comfyanonymousandGitHub 791e30ff50 Fix nan issue when quantizing fp16 tensor. (#11213) 2025-12-09 17:03:21 -05:00
comfyanonymousandGitHub d50f342c90 Fix potential issue. (#11201) 2025-12-08 23:20:04 -05:00
comfyanonymousandGitHub 3b0368aa34 Fix regression. (#11194) 2025-12-08 17:38:36 -05:00
comfyanonymousandGitHub 56fa7dbe38 Properly load the newbie diffusion model. (#11172) 
There is still one of the text encoders missing and I didn't actually test it.
 2025-12-07 07:44:55 -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
comfyanonymousandGitHub 50ca97e776 Speed up lora compute and lower memory usage by doing it in fp16. (#11161) 2025-12-06 18:36:20 -05:00
comfyanonymousandGitHub d7a0aef650 Set OCL_SET_SVM_SIZE on AMD. (#11139) 2025-12-06 00:15:21 -05:00
comfyanonymousandGitHub ae676ed105 Fix regression. (#11137) 2025-12-05 23:01:19 -05:00
comfyanonymousandGitHub 092ee8a500 Fix some custom nodes. (#11134) 2025-12-05 18:25:31 -05:00
comfyanonymousandGitHub 6fd463aec9 Fix regression when text encoder loaded directly on GPU. (#11129) 2025-12-05 15:33:16 -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 35fa091340 Forgot to put this in README. (#11112) 2025-12-04 22:52:09 -05:00
comfyanonymousandGitHub ea17add3c6 Fix case where text encoders where running on the CPU instead of GPU. (#11095) 2025-12-03 23:15:15 -05:00
comfyanonymousandGitHub ecdc8697d5 Qwen Image Lora training fix from #11090 (#11094) 2025-12-03 22:49:28 -05:00
comfyanonymousandGitHub 861817d22d Fix issue with portable updater. (#11070) 
This should fix the problem with the portable updater not working with portables created from a separate branch on the repo.

This does not affect any current portables who were all created on the master branch.
 2025-12-03 00:47:51 -05:00
comfyanonymousandGitHub b94d394a64 Support Z Image alibaba pai fun controlnets. (#11062) 
These are not actual controlnets so put it in the models/model_patches
folder and use the ModelPatchLoader + QwenImageDiffsynthControlnet node to
use it.
 2025-12-02 21:38:31 -05:00
comfyanonymousandGitHub daaceac769 Hack to make zimage work in fp16. (#11057) 2025-12-02 17:11:58 -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 f8b981ae9a Next AMD portable will have pytorch with ROCm 7.1.1 (#11002) 2025-11-30 04:21:31 -05:00
comfyanonymousandGitHub 0a6746898d Make the ScaleRope node work on Z Image and Lumina. (#10994) 2025-11-29 18:00:55 -05:00
comfyanonymousandGitHub 5151cff293 Add some missing z image lora layers. (#10980) 2025-11-28 23:55:00 -05:00
comfyanonymousandGitHub 52a32e2b32 Support some z image lora formats. (#10978) 2025-11-28 21:12:42 -05:00
comfyanonymousandGitHub 065a2fbbec Update driver link in AMD portable README (#10974) 2025-11-28 19:37:39 -05:00
comfyanonymousandGitHub f55c98a89f Disable offload stream when torch compile. (#10961) 2025-11-28 16:16:46 -05:00
comfyanonymousandGitHub 9d8a817985 Enable async offloading by default on Nvidia. (#10953) 
Add --disable-async-offload to disable it.

If this causes OOMs that go away when you --disable-async-offload please
report it.
 2025-11-27 17:46:12 -05:00
comfyanonymousandGitHub eaf68c9b5b Make lora training work on Z Image and remove some redundant nodes. (#10927) 2025-11-26 19:25:32 -05:00
comfyanonymousandGitHub dd41b74549 Add Z Image to readme. (#10924) 2025-11-26 15:36:38 -05:00
comfyanonymousandGitHub 55f654db3d Fix the CSP offline feature. (#10923) 2025-11-26 15:16:40 -05:00
comfyanonymousandGitHub f16219e3aa Add cheap latent preview for flux 2. (#10907) 
Thank you to the person who calculated them. You saved me a percent of my
time.
 2025-11-26 04:00:43 -05:00
comfyanonymousandGitHub 58b8574661 Fix Flux2 reference image mem estimation. (#10905) 2025-11-26 02:36:19 -05:00
comfyanonymousandGitHub bdb10a583f Fix loras not working on mixed fp8. (#10899) 2025-11-26 00:07:58 -05:00
comfyanonymousandGitHub 0e24dbb19f Adjustments to Z Image. (#10893) 2025-11-25 19:02:51 -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 af81cb962d Add Flux 2 support to README. (#10882) 2025-11-25 11:40:32 -05:00
comfyanonymousandGitHub 6b573ae0cb Flux 2 (#10879) 2025-11-25 10:50:19 -05:00
comfyanonymousandGitHub 015a0599d0 I found a case where this is needed (#10875) 2025-11-25 03:23:19 -05:00
comfyanonymousandGitHub acfaa5c4a1 Don't try fp8 matrix mult in quantized ops if not supported by hardware. (#10874) 2025-11-25 02:55:49 -05:00
comfyanonymousandGitHub b6805429b9 Allow pinning quantized tensors. (#10873) 2025-11-25 02:48:20 -05:00
comfyanonymousandGitHub 25022e0b09 Cleanup and fix issues with text encoder quants. (#10872) 2025-11-25 01:48:53 -05:00
comfyanonymousandGitHub 22a2644e57 Bump transformers version in requirements.txt (#10869) 2025-11-24 19:45:54 -05:00
comfyanonymousandGitHub cbd68e3d58 Add better error message for common error. (#10846) 2025-11-23 04:55:22 -05:00
comfyanonymousandGitHub d89c29f259 Add display names to Hunyuan latent video nodes. (#10837) 2025-11-22 22:51:53 -05:00
comfyanonymousandGitHub 532938b16b --disable-api-nodes now sets CSP header to force frontend offline. (#10829) 2025-11-21 17:51:55 -05:00
comfyanonymousandGitHub 3398123752 Fix wrong path. (#10821) 2025-11-20 23:39:37 -05:00
comfyanonymousGitHubkijaiRattus
 		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 f5e66d5e47 Fix ImageBatch with different channel count. (#10815) 2025-11-20 15:08:03 -05:00
comfyanonymousandGitHub cb96d4d18c Disable workaround on newer cudnn. (#10807) 2025-11-19 23:56:23 -05:00
comfyanonymousandGitHub 7601e89255 Fix workflow name. (#10806) 2025-11-19 20:17:15 -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 d526974576 Fix hunyuan 3d 2.0 (#10792) 2025-11-18 16:46:19 -05:00
comfyanonymousandGitHub 47bfd5a33f Native block swap custom nodes considered harmful. (#10783) 2025-11-18 00:26:44 -05:00
comfyanonymousandGitHub f41e5f398d Update README with new portable download link (#10778) 2025-11-17 19:59:19 -05:00
comfyanonymousandGitHub 27cbac865e Add release workflow for NVIDIA cu126 (#10777) 2025-11-17 19:04:04 -05:00
comfyanonymousandGitHub 7d6103325e Change ROCm nightly install command to 7.1 (#10764) 2025-11-16 03:01:14 -05:00
comfyanonymousandGitHub bd01d9f7fd Add left padding support to tokenizers. (#10753) 2025-11-15 06:54:40 -05:00
comfyanonymousandGitHub 443056c401 Fix custom nodes import error. (#10747) 
This should fix the import errors but will break if the custom nodes actually try to use the class.
 2025-11-14 03:26:05 -05:00
comfyanonymousandGitHub f60923590c Use same code for chroma and flux blocks so that optimizations are shared. (#10746) 2025-11-14 01:28:05 -05:00
comfyanonymousandGitHub 1ef328c007 Better instructions for the portable. (#10743) 2025-11-13 21:32:39 -05:00
comfyanonymousandGitHub 8b0b93df51 Update Python 3.14 compatibility notes in README (#10730) 2025-11-12 17:04:41 -05:00
comfyanonymousandGitHub 1199411747 Don't pin tensor if not a torch.nn.parameter.Parameter (#10718) 2025-11-11 19:33:30 -05:00
comfyanonymousandGitHub 5ebcab3c7d Update CI workflow to remove dead macOS runner. (#10704) 
* Update CI workflow to remove dead macOS runner.

* revert

* revert
 2025-11-10 15:35:29 -05:00
comfyanonymousandGitHub dea899f221 Unload weights if vram usage goes up between runs. (#10690) 2025-11-09 18:51:33 -05:00
comfyanonymousandGitHub e632e5de28 Add logging for model unloading. (#10692) 2025-11-09 18:06:39 -05:00
comfyanonymousandGitHub 2abd2b5c20 Make ScaleROPE node work on Flux. (#10686) 2025-11-08 15:52:02 -05:00
comfyanonymousandGitHub a1a70362ca Only unpin tensor if it was pinned by ComfyUI (#10677) 2025-11-07 11:15:05 -05:00
comfyanonymousandGitHub eb1c42f649 Tell users they need to upload their logs in bug reports. (#10671) 2025-11-06 20:24:28 -05:00
comfyanonymousandGitHub e05c907126 Clarify release cycle. (#10667) 2025-11-06 04:11:30 -05:00
comfyanonymousandGitHub 09dc24c8a9 Pinned mem also seems to work on AMD. (#10658) 2025-11-05 19:11:15 -05:00
comfyanonymousandGitHub 1d69245981 Enable pinned memory by default on Nvidia. (#10656) 
Removed the --fast pinned_memory flag.

You can use --disable-pinned-memory to disable it. Please report if it
causes any issues.
 2025-11-05 18:08:13 -05:00
comfyanonymousandGitHub 97f198e421 Fix qwen controlnet regression. (#10657) 2025-11-05 18:07:35 -05:00
comfyanonymousandGitHub c4a6b389de Lower ltxv mem usage to what it was before previous pr. (#10643) 
Bring back qwen behavior to what it was before previous pr.
 2025-11-04 22:47:35 -05:00
comfyanonymousandGitHub 7f3e4d486c Limit amount of pinned memory on windows to prevent issues. (#10638) 2025-11-04 17:37:50 -05:00
comfyanonymousandGitHub af4b7b5edb More fp8 torch.compile regressions fixed. (#10625) 2025-11-03 22:14:20 -05:00
comfyanonymousandGitHub 0f4ef3afa0 This seems to slow things down slightly on Linux. (#10624) 2025-11-03 21:47:14 -05:00
comfyanonymousandGitHub 6b88478f9f Bring back fp8 torch compile performance to what it should be. (#10622) 2025-11-03 19:22:10 -05:00
comfyanonymousandGitHub e199c8cc67 Fixes (#10621) 2025-11-03 17:58:24 -05:00
comfyanonymousandGitHub 0652cb8e2d Speed up torch.compile (#10620) 2025-11-03 17:37:12 -05:00
comfyanonymousandGitHub 958a17199a People should update their pytorch versions. (#10618) 2025-11-03 17:08:30 -05:00