 YunjieYu
|
5f47fc8b35
|
Update recommended setting for FLUX-Kontext
|
2025-07-12 11:48:07 +08:00 |
|
|
YunjieYu
|
a8012e85b4
|
Support FLUX-Kontext
|
2025-07-11 15:24:56 +08:00 |
|
|
YunjieYu
|
4bca908bf5
|
Support HiDream-I1-Fast
|
2025-06-22 15:42:03 +08:00 |
|
|
YunjieYu
|
bf45cdf6d6
|
Support HiDream-I1-Dev and Lumina-Image-2.0, add cache_device option
|
2025-06-15 17:39:57 +08:00 |
|
|
YunjieYu
|
9db9e3393f
|
Update README.md
|
2025-05-24 16:10:40 +08:00 |
|
|
YunjieYu
|
9dffe454bd
|
Fix compatibility issue with SkipLayerGuidanceWanVideo node
|
2025-05-23 17:57:06 +08:00 |
|
|
YunjieYu
|
3657f7f566
|
Support HiDream-I1-Full and redesigns TeaCache options
|
2025-05-22 15:29:35 +08:00 |
|
|
EvanYu
|
efe06530d4
|
Merge pull request #127 from programming-pupil/main
Enhancements and Bug Fixes for TeaCache CogVideoX Forward Pass
|
2025-05-15 17:23:50 +08:00 |
|
|
编程界的小学生
|
558156761a
|
optimize code
|
2025-05-14 16:17:07 +08:00 |
|
|
YunjieYu
|
546145dca5
|
fix compatibility issues
|
2025-04-24 18:43:43 +08:00 |
|
|
EvanYu
|
8d445e4b7b
|
Merge pull request #115 from ComfyNodePRs/update-publish-yaml
Update Github Action for Publishing to Comfy Registry
|
2025-04-07 16:51:30 +08:00 |
|
|
YunjieYu
|
274c5a5bce
|
Compatible with skip layer guidance
|
2025-03-29 18:50:30 +08:00 |
|
|
YunjieYu
|
a6140dea8c
|
Support retention mode for Wan2.1 models
|
2025-03-26 18:07:58 +08:00 |
|
|
YunjieYu
|
f0c6c56778
|
fix hunyuanvideo i2v v2 bug
|
2025-03-21 19:13:34 +08:00 |
|
|
YunjieYu
|
4a70030ccb
|
fix bug for flux pulid
|
2025-03-18 19:24:31 +08:00 |
|
|
YunjieYu
|
e28a937aa2
|
optimize LTX-Video for low VRAM device; optimize VRAM for all models
|
2025-03-17 18:48:00 +08:00 |
|
|
YunjieYu
|
7d9fd8644c
|
optimize Wan2.1 for low VRAM device; optimize VRAM
|
2025-03-13 18:45:34 +08:00 |
|
|
YunjieYu
|
2e75a8b611
|
optimize VRAM
|
2025-03-12 19:39:57 +08:00 |
|
|
YunjieYu
|
be73edb3ed
|
optimize VARM
|
2025-03-12 19:32:33 +08:00 |
|
|
YunjieYu
|
4542f76ff9
|
optimize VARM
|
2025-03-12 19:30:33 +08:00 |
|
|
YunjieYu
|
1a11412dea
|
Add max_skip_steps option; Merge TeaCache nodes; Update TeaCache for HunyuanVideo and LTX-Video
|
2025-03-10 19:23:38 +08:00 |
|
|
YunjieYu
|
b3429ef3de
|
force version update
|
2025-03-07 18:26:59 +08:00 |
|
|
YunjieYu
|
e6aafcdbf5
|
force version update
|
2025-03-07 18:12:03 +08:00 |
|
|
YunjieYu
|
fc5d2a1cde
|
fix TeaCacheForImgGen node bug
|
2025-03-07 17:44:17 +08:00 |
|
|
YunjieYu
|
1a61fe3cec
|
fix TeaCacheForImgGen node bug
|
2025-03-07 11:34:14 +08:00 |
|
|
YunjieYu
|
a2690d0e0e
|
support Wan2.1 series model
|
2025-03-06 22:12:42 +08:00 |
|
|
YunjieYu
|
c5968018fe
|
support Wan2.1 series model
|
2025-03-06 22:10:55 +08:00 |
|
|
YunjieYu
|
71c535a082
|
support Wan2.1 series model
|
2025-03-06 21:17:28 +08:00 |
|
|
YunjieYu
|
062efbab2e
|
Support SkyReels I2V Hunyuan Model
|
2025-02-20 16:14:19 +08:00 |
|
|
EvanYu
|
be7222aeae
|
Merge pull request #50 from maedtb/patch-1
Fix error when using SkyReels I2V Hunyuan Model
|
2025-02-20 16:07:41 +08:00 |
|
|
maedtb
|
3597bb87aa
|
Fix error when using SkyReels I2V Hunyuan Model
The number of out channels on the SkyReels Image-to-Video Hunyuan model is 32, compared to the normal 16. This change is the same fix applied to ComfyUI directly.
See: https://github.com/comfyanonymous/ComfyUI/commit/acc152b674fd1c983acc6efd8aedbeb380660c0c#diff-828ff060ac292e5b8eff646d924ade3720f1500a17b42ebdc3034c193ed4b597
|
2025-02-19 06:20:46 -05:00 |
|
|
YunjieYu
|
61636b6503
|
fix Compile Model node bug
|
2025-02-11 18:56:52 +08:00 |
|
|
YunjieYu
|
4c8bc02377
|
fix Compile Model node bug
|
2025-02-11 18:28:32 +08:00 |
|
|
EvanYu
|
4b24cea8db
|
Merge pull request #47 from TangYanxin/main
fix: 解决使用Compile Model 节点，LoRA失效的问题
|
2025-02-11 17:45:09 +08:00 |
|
|
TangYanxin
|
97d8ae3cb2
|
fix: 解决使用Compile Model 节点，LoRA失效的问题
|
2025-02-11 16:27:13 +08:00 |
|
|
snomiao
|
3d4f933269
|
chore(publish): update GitHub Actions workflow for node publishing
- Add write permissions for issues in the workflow
- Update publish-node-action to use version v1 instead of main
|
2025-01-25 17:33:45 +00:00 |
|
|
YunjieYu
|
94f536390d
|
add requirements.txt
|
2025-01-17 20:37:04 +08:00 |
|
|
EvanYu
|
e63399347c
|
Merge pull request #36 from DG266/main
Add requirements.txt
|
2025-01-17 20:23:18 +08:00 |
|
|
DG266
|
b03caf1ec6
|
Add requirements.txt
|
2025-01-17 12:54:51 +01:00 |
|
|
YunjieYu
|
904e96b1a4
|
update readme
|
2025-01-17 16:20:03 +08:00 |
|
|
EvanYu
|
3fc3127daa
|
Merge pull request #33 from TangYanxin/main
Update README.md
|
2025-01-17 16:01:09 +08:00 |
|
|
唐焱鑫
|
ab7ae00676
|
Merge branch 'main' into main
|
2025-01-17 15:45:17 +08:00 |
|
|
YunjieYu
|
5b3d9f1b7a
|
Compile Model add eager and aot_eager backend.
|
2025-01-17 15:07:37 +08:00 |
|
|
YunjieYu
|
a40c99dc56
|
Support CogVideoX
|
2025-01-17 12:09:50 +08:00 |
|
|
唐焱鑫
|
a2fd005845
|
Update README.md
|
2025-01-16 19:47:54 +08:00 |
|
|
YunjieYu
|
992a5b483c
|
Support PuLID-FLUX
|
2025-01-15 12:34:55 +08:00 |
|
|
EvanYu
|
9bc454e309
|
Merge pull request #25 from fantacytyx/main
support flux pulid, and fix bug about rel_l1_thresh
|
2025-01-15 11:40:43 +08:00 |
|
|
TangYanxin
|
c4fa3e6460
|
feat: If rel_l1_thresh==0 doe‘t execute TeaCache logic
|
2025-01-15 09:56:34 +08:00 |
|
|
TangYanxin
|
be41e9ad9f
|
Fixed: When there are multiple TeaCache nodes in a workflow, the rel_l1_thresh value is always the value of the last TeaCache node
|
2025-01-15 09:22:28 +08:00 |
|
|
TangYanxin
|
a0750c4e6f
|
support flux pulid
|
2025-01-14 22:41:36 +08:00 |
|