doctorpangloss
351731557f
Use 3060 as runner
2025-05-19 20:26:51 -07:00
doctorpangloss
6d8deff056
Switch to uv for packaging
2025-05-19 15:58:08 -07:00
doctorpangloss
a3ad9bdb1a
fix legacy kwargs
2025-05-17 16:10:54 -07:00
Benjamin Berman
bbf5b9d6cf
Merge branch 'cmdline-fixes'
2025-05-16 05:27:16 -07:00
doombubbles and Benjamin Berman
9e0522b7a8
Update ideogram nodes to v3
2025-05-16 05:25:44 -07:00
Benjamin Berman
c74cf3866f
switch to hatchling
2025-05-16 05:25:29 -07:00
Benjamin Berman
b6d3f1fb08
Accept workflows from the command line
2025-05-07 14:53:39 -07:00
doombubbles
6a06706d00
Update ideogram nodes to v3
2025-05-01 11:44:23 -07:00
Benjamin Berman
da2cbf7c91
move and fix main
2025-04-30 11:59:59 -07:00
Benjamin Berman
eed79e210e
move hook breaker
2025-04-30 11:52:33 -07:00
Benjamin Berman
aa11a31717
hook breaker
2025-04-30 11:52:20 -07:00
Benjamin Berman
84ec6a53f2
main.py stub
2025-04-29 12:02:27 -07:00
Benjamin Berman
b5e376a3d0
move main.py
2025-04-29 12:01:55 -07:00
Benjamin Berman
df6a3cf8cb
main.py from upstream
2025-04-29 12:01:34 -07:00
Benjamin Berman
0aa4143885
remove main.py
2025-04-29 12:00:31 -07:00
Benjamin Berman
c9598ec26d
include curl
2025-04-24 10:23:34 -07:00
Benjamin Berman
4015e59be5
update workflows and tweak installation script
2025-04-24 10:20:19 -07:00
Benjamin Berman
480b59b913
Migrate to pure pyproject.toml and uv for significantly faster and correct installation, add model paths for flux all in ones, and fix PathsList bug
2025-04-24 10:01:36 -07:00
doctorpangloss
17b14110ab
Update to latest ComfyUI
2025-04-21 14:11:56 -07:00
doctorpangloss
5823497d55
Merge branch 'master' of github.com:comfyanonymous/ComfyUI
2025-04-21 13:14:36 -07:00
comfyanonymous and GitHub
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 and GitHub
b6fd3ffd10
Populate AUTH_TOKEN_COMFY_ORG hidden input ( #7709 )
2025-04-21 14:39:45 -04:00
comfyanonymous and GitHub
11b72c9c55
CLIPTextEncodeHiDream. ( #7703 )
2025-04-21 02:41:51 -04:00
comfyanonymous and GitHub
2c735c13b4
Slightly better fix for #7687
2025-04-20 11:33:27 -04:00
comfyanonymous
fd27494441
Use empty t5 of size 128 for hidream, seems to give closer results.
2025-04-19 19:49:40 -04:00
power88 and GitHub
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 and GitHub
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 and GitHub
dc300a4569
Add wanfun template workflows. ( #7678 )
2025-04-19 15:21:46 -04:00
Chenlei Hu and GitHub
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 and GitHub
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 and GitHub
34e06bf7ec
add support to output camera state ( #7582 )
2025-04-18 02:52:18 -04:00
Chenlei Hu and GitHub
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 and GitHub
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
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 and GitHub
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
doctorpangloss