thot experiment
337c6bcd15
Native LotusD Implementation ( #7125 )
...
* draft pass at a native comfy implementation of Lotus-D depth and normal est
* fix model_sampling kludges
* fix ruff
---------
Co-authored-by: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com>
2025-03-21 14:04:15 -04:00
Chenlei Hu
52dd1f9ace
Update frontend to 1.14 ( #7343 )
2025-03-21 13:50:09 -04:00
comfyanonymous
03d5bbf1b3
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
Chenlei Hu
c829e4ee2d
Add backend primitive nodes ( #7328 )
...
* Add backend primitive nodes
* Add control after generate to int primitive
2025-03-21 01:47:18 -04:00
Chenlei Hu
5f60fdbf9f
Update frontend to 1.13 ( #7331 )
2025-03-21 00:17:36 -04:00
comfyanonymous
5100ca7361
A few fixes for the hunyuan3d models.
2025-03-20 04:52:31 -04:00
comfyanonymous
a3c96c7cf6
Fix orientation of hunyuan 3d model.
2025-03-19 19:55:24 -04:00
comfyanonymous
2f17e6734c
Initial Hunyuan3Dv2 implementation.
...
Supports the multiview, mini, turbo models and VAEs.
2025-03-19 16:52:58 -04:00
comfyanonymous
35324c6a52
Allow disabling pe in flux code for some other models.
2025-03-18 05:09:25 -04:00
comfyanonymous
fd7a7c66e8
Fix regression with clip vision.
2025-03-17 13:56:11 -04:00
comfyanonymous
69c6ac42da
Add support for giant dinov2 image encoder.
2025-03-17 05:53:54 -04:00
comfyanonymous
7761e410ec
Cleanup code.
2025-03-16 06:29:12 -04:00
Jedrzej Kosinski
b7246311db
Call unpatch_hooks at the start of ModelPatcher.partially_unload ( #7253 )
...
* Call unpatch_hooks at the start of ModelPatcher.partially_unload
* Only call unpatch_hooks in partially_unload if lowvram is possible
2025-03-16 06:02:45 -04:00
chaObserv
193e847c21
Guard the edge cases of noise term in er_sde ( #7265 )
2025-03-16 06:02:25 -04:00
comfyanonymous
83d3e0cce5
Allow loading diffusion model files with the "Load Checkpoint" node.
2025-03-15 08:27:49 -04:00
comfyanonymous
3f02ca182d
Show a better error message if the VAE is invalid.
2025-03-15 08:26:36 -04:00
Christian Byrne
2233490ddd
hotfix fe ( #7244 )
2025-03-15 01:38:10 -04:00
Chenlei Hu
9aa12db9fa
Update frontend to 1.12.9 ( #7236 )
...
* Update frontend to 1.12.9
* Update requirements.txt
2025-03-14 18:17:26 -04:00
comfyanonymous
46c332a93f
Remove useless code.
2025-03-14 18:10:37 -04:00
comfyanonymous
95649bd3bb
Make the SkipLayerGuidanceDIT node work on WAN.
2025-03-14 10:55:19 -04:00
FeepingCreature
1434c8d833
Tolerate missing @torch.library.custom_op ( #7234 )
...
This can happen on Pytorch versions older than 2.4.
2025-03-14 09:51:26 -04:00
FeepingCreature
d466fbcae5
Add --use-flash-attention flag. ( #7223 )
...
* Add --use-flash-attention flag.
This is useful on AMD systems, as FA builds are still 10% faster than Pytorch cross-attention.
2025-03-14 03:22:41 -04:00
comfyanonymous
8a845e4e3e
Fix.
2025-03-13 15:03:18 -04:00
comfyanonymous
7385b43e8e
Print mac version.
2025-03-13 10:05:40 -04:00
Chenlei Hu
8867b89d8f
Add codeowner for comfy/comfy_types ( #7213 )
2025-03-12 17:30:00 -04:00
Chenlei Hu
6aac29ba5f
[NodeDef] Add documentation on multi_select input option ( #7212 )
2025-03-12 17:29:39 -04:00
chaObserv
bca2fadabc
Ensure the extra_args in dpmpp sde series ( #7204 )
2025-03-12 17:28:59 -04:00
comfyanonymous
d37d608f4c
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
Chenlei Hu
2d4abacce0
Add unwrap widget value support ( #7197 )
...
* Add unwrap widget value support
* nit
2025-03-12 06:39:14 -04:00
chaObserv
2e11c2bf43
Add er_sde sampler ( #7187 )
2025-03-12 02:42:37 -04:00
comfyanonymous
4604cb4580
Fix error saving some latents.
2025-03-11 15:07:16 -04:00
comfyanonymous
fd4f6c219d
Merge pull request #7143 from christian-byrne/fix-remote-widget-node
...
Fix LoadImageOutput node
2025-03-11 04:30:25 -04:00
comfyanonymous
8905a5ecd9
Merge pull request #7179 from comfyanonymous/ignore_fe_package
...
Only check frontend package if using default frontend
2025-03-11 03:45:02 -04:00
huchenlei
ec5307b88f
Access package version
2025-03-10 20:43:59 -04:00
comfyanonymous
81179b3401
Support control loras on Wan.
2025-03-10 17:23:13 -04:00
Chenlei Hu
20648f90e6
nit
2025-03-10 15:19:59 -04:00
Chenlei Hu
6c3a2f1750
Fix unit test
2025-03-10 15:19:52 -04:00
Chenlei Hu
f60235406b
nit
2025-03-10 15:14:40 -04:00
Chenlei Hu
db14befaf5
nit
2025-03-10 15:10:40 -04:00
Chenlei Hu
fae046ca73
Only check frontend package if using default frontend
2025-03-10 15:07:44 -04:00
comfyanonymous
ed40451b6d
Temporarily revert fix to give time for people to update their nodes.
2025-03-10 06:30:17 -04:00
comfyanonymous
b56985887a
Hack to fix broken manager.
2025-03-10 06:15:17 -04:00
Andrew Kvochko
34505fa2f7
ltxv: relax frame_idx divisibility for single frames. ( #7146 )
...
This commit relaxes divisibility constraint for single-frame
conditionings. For single frames, the index can be arbitrary, while
multi-frame conditionings (>= 9 frames) must still be aligned to 8
frames.
Co-authored-by: Andrew Kvochko <a.kvochko@lightricks.com>
2025-03-10 04:11:48 -04:00
comfyanonymous
2e15e002b5
Prevent custom nodes from accidentally overwriting global modules.
2025-03-10 03:33:41 -04:00
Terry Jia
cef91b4815
remove unused params ( #6931 )
2025-03-09 14:07:09 -04:00
bymyself
4087838026
remove overrides
2025-03-09 03:46:08 -07:00
comfyanonymous
1c6f208a45
Fix issues with new hunyuan img2vid model and bumb version to v0.3.26
2025-03-09 05:07:22 -04:00
Jedrzej Kosinski
707bbf54f0
When cached_hook_patches contain weights for hooks, only use hook_backup for unused keys ( #7067 )
2025-03-09 04:26:31 -04:00
comfyanonymous
566ba82e8d
ComfyUI version v0.3.25
2025-03-09 03:30:20 -04:00
comfyanonymous
bebc72d093
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
