comfyanonymous
5d0d4ee98a
Add strength control for vace. ( #7717 )
2025-04-21 19:36:20 -04:00
Alexander G. Morano
9d57b8afd8
Update nodes_primitive.py ( #7716 )
...
Allow FLOAT and INT types to support negative numbers.
Caps the numbers at the user's own system min and max.
2025-04-21 18:51:31 -04:00
filtered
5d51794607
Add node type hint for socketless option ( #7714 )
...
* Add node type hint for socketless option
* nit - Doc
2025-04-21 16:13:00 -04:00
comfyanonymous
ce22f687cc
Support for WAN VACE preview model. ( #7711 )
...
* Support for WAN VACE preview model.
* Remove print.
2025-04-21 14:40:29 -04:00
Chenlei Hu
b6fd3ffd10
Populate AUTH_TOKEN_COMFY_ORG hidden input ( #7709 )
2025-04-21 14:39:45 -04:00
Dr.Lt.Data
9c2eb2c1dd
Merge branch 'master' into dr-support-pip-cm
2025-04-22 02:24:26 +09:00
comfyanonymous
11b72c9c55
CLIPTextEncodeHiDream. ( #7703 )
2025-04-21 02:41:51 -04:00
Dr.Lt.Data
ec82eea1f1
Merge branch 'master' into dr-support-pip-cm
2025-04-21 12:06:29 +09:00
comfyanonymous
2c735c13b4
Slightly better fix for #7687
2025-04-20 11:33:27 -04:00
Dr.Lt.Data
4fafc0c58d
Merge branch 'master' into dr-support-pip-cm
2025-04-20 19:08:51 +09:00
comfyanonymous
fd27494441
Use empty t5 of size 128 for hidream, seems to give closer results.
2025-04-19 19:49:40 -04:00
power88
f43e1d7f41
Hidream: Allow loading hidream text encoders in CLIPLoader and DualCLIPLoader ( #7676 )
...
* Hidream: Allow partial loading text encoders
* reformat code for ruff check.
2025-04-19 19:47:30 -04:00
Yoland Yan
4486b0d0ff
Update CODEOWNERS and add christian-byrne ( #7663 )
2025-04-19 17:23:31 -04:00
comfyanonymous
636d4bfb89
Fix hard crash when the spiece tokenizer path is bad.
2025-04-19 15:55:43 -04:00
Robin Huang
dc300a4569
Add wanfun template workflows. ( #7678 )
2025-04-19 15:21:46 -04:00
Chenlei Hu
f3b09b9f2d
[BugFix] Update frontend to 1.16.9 ( #7655 )
...
Backport https://github.com/Comfy-Org/ComfyUI_frontend/pull/3505
2025-04-18 15:12:42 -04:00
comfyanonymous
7ecd5e9614
Increase freq_cutoff in FreSca node.
2025-04-18 03:16:16 -04:00
City
2383a39e3b
Replace CLIPType if with getattr ( #7589 )
...
* Replace CLIPType if with getattr
* Forgot to remove breakpoint from testing
2025-04-18 02:53:36 -04:00
Terry Jia
34e06bf7ec
add support to output camera state ( #7582 )
2025-04-18 02:52:18 -04:00
Chenlei Hu
55822faa05
[Type] Annotate graph.get_input_info ( #7386 )
...
* [Type] Annotate graph.get_input_info
* nit
* nit
2025-04-17 21:02:24 -04:00
comfyanonymous
880c205df1
Add hidream to readme.
2025-04-17 16:58:27 -04:00
comfyanonymous
3dc240d089
Make fresca work on multi dim.
2025-04-17 15:46:41 -04:00
BVH
19373aee75
Add FreSca node ( #7631 )
2025-04-17 15:24:33 -04:00
comfyanonymous
93292bc450
ComfyUI version 0.3.29
2025-04-17 14:45:01 -04:00
Christian Byrne
05d5a75cdc
Update frontend to 1.16 (Install templates as pip package) ( #7623 )
...
* install templates as pip package
* Update requirements.txt
* bump templates version to include hidream
---------
Co-authored-by: Chenlei Hu <hcl@comfy.org>
2025-04-17 14:25:33 -04:00
comfyanonymous
eba7a25e7a
Add WanFirstLastFrameToVideo node to use the new model.
2025-04-17 13:23:22 -04:00
comfyanonymous
dbcfd092a2
Set default context_img_len to 257
2025-04-17 12:42:34 -04:00
comfyanonymous
c14429940f
Support loading WAN FLF model.
2025-04-17 12:04:48 -04:00
comfyanonymous
0d720e4367
Don't hardcode length of context_img in wan code.
2025-04-17 06:25:39 -04:00
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
Chenlei Hu
cce1d9145e
[Type] Mark input options NotRequired ( #7614 )
2025-04-16 15:41:00 -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
Dr.Lt.Data
d2ed1dcb9a
Merge branch 'master' into dr-support-pip-cm
2025-04-15 23:04:27 +09:00
comfyanonymous
8a438115fb
add RMSNorm to comfy.ops
2025-04-14 18:00:33 -04:00
Dr.Lt.Data
94f61c6378
add --enable-manager-legacy-ui
2025-04-15 01:36:17 +09:00
comfyanonymous
a14c2fc356
ComfyUI version v0.3.28
2025-04-13 12:21:12 -07:00
JNP
9ee6ca99d8
add_optimalsteps ( #7584 )
...
Co-authored-by: bebebe666 <jianningpei@tencent.com>
2025-04-12 20:33:36 -04:00
comfyanonymous
bb495cc9b8
Print python version in log.
2025-04-12 18:58:34 -04:00
chaObserv
e51d9ba5fc
Add SEEDS (stage 2 & 3 DP) sampler ( #7580 )
...
* Add seeds stage 2 & 3 (DP) sampler
* Change the name to SEEDS in comment
2025-04-12 18:36:08 -04:00
Christian Byrne
c87a06f934
Update filter_files_content_types to support filtering 3d models ( #7572 )
...
* support 3d model filtering
* fix lint error: blank line contains whitespace
* add model extensions to test runner mimetype cache manually
* use unittest.mock.patch
* remove mtl file from testcase (actually plaintext support file)
2025-04-12 18:30:39 -04:00
catboxanon
1714a4c158
Add CublasOps support ( #7574 )
...
* CublasOps support
* Guard CublasOps behind --fast arg
2025-04-12 18:29:15 -04:00
Christian Byrne
73ecb75a3d
filter image files in load image dropdown ( #7573 )
2025-04-12 18:27:59 -04:00
Dr.Lt.Data
418eaed42c
fixed: Ensure that comfyui_manager's prestartup always runs, even when --disable-all-custom-nodes is used.
...
feat: Disable specific custom nodes according to the policy of `comfyui_manager`.
2025-04-12 21:53:57 +09:00
Dr.Lt.Data
cc975e5f0b
add comfyui_manager to requirements.txt
...
It's still in the development stage, so the version is not pinned yet.
2025-04-12 19:11:02 +09:00
Dr.Lt.Data
311f64ac83
Merge branch 'master' into dr-support-pip-cm
2025-04-12 19:08:15 +09:00
