comfyanonymous
1fc00ba4b6
Make hidream work with any latent resolution.
2025-04-16 18:34:14 -04:00
comfyanonymous
9899d187b1
Limit T5 to 128 tokens for HiDream: #7620
2025-04-16 18:07:55 -04:00
comfyanonymous
f00f340a56
Reuse code from flux model.
2025-04-16 17:43:55 -04:00
comfyanonymous
b4dc03ad76
Fix issue on old torch.
2025-04-16 04:53:56 -04:00
comfyanonymous
9ad792f927
Basic support for hidream i1 model.
2025-04-15 17:35:05 -04:00
comfyanonymous
6fc5dbd52a
Cleanup.
2025-04-15 12:13:28 -04:00
comfyanonymous
3e8155f7a3
More flexible long clip support.
...
Add clip g long clip support.
Text encoder refactor.
Support llama models with different vocab sizes.
2025-04-15 10:32:21 -04:00
comfyanonymous
8a438115fb
add RMSNorm to comfy.ops
2025-04-14 18:00:33 -04:00
comfyanonymous
a14c2fc356
ComfyUI version v0.3.28
2025-04-13 12:21:12 -07:00
comfyanonymous
bb495cc9b8
Print python version in log.
2025-04-12 18:58:34 -04:00
comfyanonymous
22ad513c72
Refactor node cache code to more easily add other types of cache.
2025-04-11 07:16:52 -04:00
comfyanonymous
a26da20a76
Fix custom nodes not importing when path contains a dot.
2025-04-10 03:37:52 -04:00
comfyanonymous
ab31b64412
Make "surface net" the default in the VoxelToMesh node.
2025-04-09 09:42:08 -04:00
comfyanonymous
2f7d8159c3
Show the user an error when the controlnet file is invalid.
2025-04-08 08:11:59 -04:00
comfyanonymous
70d7242e57
Support the wan fun reward loras.
2025-04-07 05:01:47 -04:00
comfyanonymous
49b732afd5
Show a proper error to the user when a vision model file is invalid.
2025-04-06 22:43:56 -04:00
comfyanonymous
3bfe4e5276
Support 512 siglip model.
2025-04-05 07:01:01 -04:00
comfyanonymous
3a100b9a55
Disable partial offloading of audio VAE.
2025-04-04 21:24:56 -04:00
comfyanonymous
721253cb05
Fix problem.
2025-04-03 20:57:59 -04:00
comfyanonymous
3d2e3a6f29
Fix alpha image issue in more nodes.
2025-04-02 19:32:49 -04:00
comfyanonymous
ab5413351e
Fix comment.
...
This function does not support quads.
2025-04-01 14:09:31 -04:00
comfyanonymous
548457bac4
Fix alpha channel mismatch on destination in ImageCompositeMasked
2025-03-31 20:59:12 -04:00
comfyanonymous
0b4584c741
Fix latent composite node not working when source has alpha.
2025-03-30 21:47:05 -04:00
comfyanonymous
a3100c8452
Remove useless code.
2025-03-29 20:12:56 -04:00
comfyanonymous
2d17d8910c
Don't error if wan concat image has extra channels.
2025-03-28 08:49:29 -04:00
comfyanonymous
0a1f8869c9
Add WanFunInpaintToVideo node for the Wan fun inpaint models.
2025-03-27 11:13:27 -04:00
comfyanonymous
3661c833bc
Support the WAN 2.1 fun control models.
...
Use the new WanFunControlToVideo node.
2025-03-26 19:54:54 -04:00
comfyanonymous
84fdaf7b0e
Add CFGZeroStar node.
...
Works on all models that use a negative prompt but is meant for rectified
flow models.
2025-03-26 05:09:52 -04:00
comfyanonymous
8edc1f44c1
Support more float8 types.
2025-03-25 05:23:49 -04:00
comfyanonymous
eade1551bb
Add Hunyuan3D to readme.
2025-03-24 07:14:32 -04:00
comfyanonymous
581a9991ff
Add model merging node for WAN 2.1
2025-03-23 08:06:36 -04:00
comfyanonymous
e471c726e5
Fallback to pytorch attention if sage attention fails.
2025-03-22 15:45:56 -04:00
comfyanonymous
75c1c757d9
ComfyUI version v0.3.27
2025-03-21 20:09:54 -04:00
comfyanonymous
d9fa9d307f
Automatically set the right sampling type for lotus.
2025-03-21 14:19:37 -04:00
comfyanonymous
0956107170
Nodes to convert images to YUV and back.
...
Can be used to convert an image to black and white.
2025-03-21 06:32:44 -04:00
comfyanonymous
3872b43d4b
A few fixes for the hunyuan3d models.
2025-03-20 04:52:31 -04:00
comfyanonymous
32ca0805b7
Fix orientation of hunyuan 3d model.
2025-03-19 19:55:24 -04:00
comfyanonymous
11f1b41bab
Initial Hunyuan3Dv2 implementation.
...
Supports the multiview, mini, turbo models and VAEs.
2025-03-19 16:52:58 -04:00
comfyanonymous
3b19fc76e3
Allow disabling pe in flux code for some other models.
2025-03-18 05:09:25 -04:00
comfyanonymous
50614f1b79
Fix regression with clip vision.
2025-03-17 13:56:11 -04:00
comfyanonymous
6dc7b0bfe3
Add support for giant dinov2 image encoder.
2025-03-17 05:53:54 -04:00
comfyanonymous
e8e990d6b8
Cleanup code.
2025-03-16 06:29:12 -04:00
comfyanonymous
55a1b09ddc
Allow loading diffusion model files with the "Load Checkpoint" node.
2025-03-15 08:27:49 -04:00
comfyanonymous
3c3988df45
Show a better error message if the VAE is invalid.
2025-03-15 08:26:36 -04:00
comfyanonymous
a2448fc527
Remove useless code.
2025-03-14 18:10:37 -04:00
comfyanonymous
6a0daa79b6
Make the SkipLayerGuidanceDIT node work on WAN.
2025-03-14 10:55:19 -04:00
comfyanonymous
35504e2f93
Fix.
2025-03-13 15:03:18 -04:00
comfyanonymous
299436cfed
Print mac version.
2025-03-13 10:05:40 -04:00
comfyanonymous
f4411250f3
Repeat frontend version warning at the end.
...
This way someone running ComfyUI with the command line is more likely to
actually see it.
2025-03-12 07:13:40 -04:00
comfyanonymous
2330754b0e
Fix error saving some latents.
2025-03-11 15:07:16 -04:00
comfyanonymous
ca8efab79f
Support control loras on Wan.
2025-03-10 17:23:13 -04:00
comfyanonymous
b779349b55
Temporarily revert fix to give time for people to update their nodes.
2025-03-10 06:30:17 -04:00
comfyanonymous
35e2dcf5d7
Hack to fix broken manager.
2025-03-10 06:15:17 -04:00
comfyanonymous
6f8e766509
Prevent custom nodes from accidentally overwriting global modules.
2025-03-10 03:33:41 -04:00
comfyanonymous
9aac21f894
Fix issues with new hunyuan img2vid model and bumb version to v0.3.26
2025-03-09 05:07:22 -04:00
comfyanonymous
2bc4b5968f
ComfyUI version v0.3.25
2025-03-09 03:30:20 -04:00
comfyanonymous
7395b0c0d1
Support new hunyuan video i2v model.
...
Use the new "v2 (replace)" guidance type in HunyuanImageToVideo and set
image_interleave to 4 on the "Text Encode Hunyuan Video" node.
2025-03-08 20:34:47 -05:00
comfyanonymous
0952569493
Fix stable cascade VAE on some lowvram machines.
2025-03-08 20:24:04 -05:00
comfyanonymous
29832b3b61
Warn if frontend package is older than the one in requirements.txt
2025-03-08 03:51:36 -05:00
comfyanonymous
be4e760648
Add an image_interleave option to the Hunyuan image to video encode node.
...
See the tooltip for what it does.
2025-03-07 19:56:26 -05:00
comfyanonymous
c3d9cc4592
Print the frontend version in the log.
2025-03-07 19:56:26 -05:00
comfyanonymous
ebbb920163
Add back taesd to nightly package.
2025-03-07 14:56:09 -05:00
comfyanonymous
d60fe0af4a
Reduce size of nightly package.
2025-03-07 08:30:01 -05:00
comfyanonymous
5dbd250965
Update nightly instructions in readme.
2025-03-07 07:57:59 -05:00
comfyanonymous
4ab1875283
Add .bat file to nightly package to run with fp16 accumulation.
2025-03-07 07:45:40 -05:00
comfyanonymous
11b1f27cb1
Set WAN default compute dtype to fp16.
2025-03-07 04:52:36 -05:00
comfyanonymous
70e15fd743
No need for scale_input when fp8 matrix mult is disabled.
2025-03-07 04:49:20 -05:00
comfyanonymous
e1474150de
Support fp8_scaled diffusion models that don't use fp8 matrix mult.
2025-03-07 04:39:21 -05:00
comfyanonymous
a13125840c
ComfyUI version v0.3.24
2025-03-06 13:53:48 -05:00
comfyanonymous
dfa36e6855
Fix some things breaking when embeddings fail to apply.
2025-03-06 13:31:55 -05:00
comfyanonymous
0124be4d93
ComfyUI version v0.3.23
2025-03-06 04:10:12 -05:00
comfyanonymous
29a70ca101
Support HunyuanVideo image to video model.
2025-03-06 03:07:15 -05:00
comfyanonymous
0bef826a98
Support llava clip vision model.
2025-03-06 00:24:43 -05:00
comfyanonymous
85ef295069
Make applying embeddings more efficient.
...
Adding new tokens no longer makes a whole copy of the embeddings weight
which can be massive on certain models.
2025-03-05 17:34:38 -05:00
comfyanonymous
889519971f
Bump ComfyUI version to v0.3.22
2025-03-05 10:06:37 -05:00
comfyanonymous
76739c23c3
Revert "Partially revert last commit."
...
This reverts commit a80bc822a2
2025-03-05 09:57:40 -05:00
comfyanonymous
a80bc822a2
Partially revert last commit.
2025-03-05 08:58:44 -05:00
comfyanonymous
6d45ffbe23
Bump ComfyUI version to v0.3.21
2025-03-05 08:05:22 -05:00
comfyanonymous
77633ba77d
Remove unused variable.
2025-03-05 07:31:47 -05:00
comfyanonymous
30e6cfb1a0
Fix LTXVPreprocess on resolutions that are not multiples of 2.
2025-03-05 07:18:13 -05:00
comfyanonymous
dc134b2fdb
Bump ComfyUI version to v0.3.20
2025-03-05 06:28:14 -05:00
comfyanonymous
369b079ff6
Fix lowvram issue with ltxv vae.
2025-03-05 05:26:08 -05:00
comfyanonymous
9c9a7f012a
Adjust ltxv memory factor.
2025-03-05 05:16:05 -05:00
comfyanonymous
93fedd92fe
Support LTXV 0.9.5.
...
Credits: Lightricks team.
2025-03-05 00:13:49 -05:00
comfyanonymous
745b13649b
Add update instructions for the portable.
2025-03-04 23:34:36 -05:00
comfyanonymous
65042f7d39
Make it easier to set a custom template for hunyuan video.
2025-03-04 09:26:05 -05:00
comfyanonymous
7c7c70c400
Refactor skyreels i2v code.
2025-03-04 00:15:45 -05:00
comfyanonymous
8362199ee7
Bump ComfyUI version to v0.3.19
2025-03-03 19:18:37 -05:00
comfyanonymous
f86c724ef2
Temporal area composition.
...
New ConditioningSetAreaPercentageVideo node.
2025-03-03 06:50:31 -05:00
comfyanonymous
6752a826f6
Make the missing frontend package error more obvious.
2025-03-02 15:43:56 -05:00
comfyanonymous
9af6320ec9
Make 2d area composition nodes work on video models.
2025-03-02 08:19:16 -05:00
comfyanonymous
6f81cd8973
Change defaults in WanImageToVideo node.
2025-03-01 19:26:48 -05:00
comfyanonymous
4dc6709307
Rename argument in last commit and document the options.
2025-03-01 02:43:49 -05:00
comfyanonymous
cf0b549d48
--fast now takes a number as argument to indicate how fast you want it.
...
The idea is that you can indicate how much quality vs speed you want.
At the moment:
--fast 2 enables fp16 accumulation if your pytorch supports it.
--fast 5 enables fp8 matrix mult on fp8 models and the optimization above.
--fast without a number enables all optimizations.
2025-02-28 02:48:20 -05:00
comfyanonymous
eb4543474b
Use fp16 for intermediate for fp8 weights with --fast if supported.
2025-02-28 02:17:50 -05:00
comfyanonymous
1804397952
Use fp16 if checkpoint weights are fp16 and the model supports it.
2025-02-27 16:39:57 -05:00
comfyanonymous
f4dac8ab6f
Wan code small cleanup.
2025-02-27 07:22:42 -05:00
comfyanonymous
b07f116dea
Bump ComfyUI version to v0.3.18
2025-02-26 21:19:14 -05:00
comfyanonymous
714f728820
Add to README that the Wan model is supported.
2025-02-26 20:48:50 -05:00
comfyanonymous
92d8d15300
Readme changes.
...
Instructions shouldn't recommend to run comfyui with --listen
2025-02-26 20:47:08 -05:00
comfyanonymous