wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-05-11 01:32:31 +08:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity
672 Commits 208 Branches 147 Tags 1.8 GiB
03dabd2f56
Commit Graph

34 Commits

Author SHA1 Message Date
missionfloyd
03dabd2f56 Fix rotate node with batch_size > 1 2023-04-27 20:45:58 -06:00
missionfloyd
7b64c38d52 Update nodes_post_processing.py 2023-04-14 13:52:19 -06:00
missionfloyd
cf2b046ec3 Don't need to create an empty mask 2023-04-14 13:32:21 -06:00
missionfloyd
2bd435c25c Rename inputs 2023-04-13 22:01:14 -06:00
missionfloyd
a20163eb84 Composite images of different sizes 
resample option is used when scaling mask
 2023-04-13 21:54:41 -06:00
missionfloyd
46d0fa6424 Make mask optional 2023-04-13 21:19:10 -06:00
missionfloyd
71f939c3ed Add translate option to composite 2023-04-13 21:00:53 -06:00
missionfloyd
e570d027a3
Remove print statements 2023-04-13 10:57:08 -06:00
missionfloyd
a6347a959c
Separate x/y values for rotate 2023-04-13 10:51:40 -06:00
missionfloyd
46a57e286d
Correct height, width variables 2023-04-12 21:25:40 -06:00
missionfloyd
f5474109a4
Add center, translate options to rotate 
Center and translate take X,Y coordinates
Change min to -360
 2023-04-11 21:42:19 -06:00
missionfloyd
fcc561261d
Use torch for extract, split, merge 2023-04-11 20:17:00 -06:00
missionfloyd
9b40cd3f89
Add expand option to rotate 2023-04-10 21:20:42 -06:00
missionfloyd
bc54b69c59
Change transpose to torch 2023-04-10 20:23:15 -06:00
missionfloyd
70564aebb6
Name split node outputs 2023-04-10 02:38:46 -06:00
missionfloyd
8c16b98008
Image composite node 2023-04-09 22:36:39 -06:00
missionfloyd
d414157701
Fix transpose with non-square images 2023-04-09 19:19:14 -06:00
missionfloyd
97c7a402d7
Merge channels node 2023-04-09 19:08:17 -06:00
missionfloyd
6f7abd9497
Image split, getchannel nodes 2023-04-09 18:48:05 -06:00
missionfloyd
d36ad5d958
Add transpose and rotate nodes 2023-04-08 20:43:43 -06:00
comfyanonymous
871a76b77b Rename and reorganize post processing nodes. 2023-04-04 22:54:33 -04:00
comfyanonymous
af291e6f69 Convert line endings to unix. 2023-04-04 13:56:13 -04:00
EllangoK
56196ab0f7 use common_upcale in blend 2023-04-04 10:57:34 -04:00
EllangoK
fa2febc062 blend supports any size, dither -> quantize 2023-04-03 09:52:04 -04:00
EllangoK
4c7a9dbcb6 adds Blend, Blur, Dither, Sharpen nodes 2023-04-02 18:44:27 -04:00
comfyanonymous
809bcc8ceb Add support for unCLIP SD2.x models. 
See _for_testing/unclip in the UI for the new nodes.

unCLIPCheckpointLoader is used to load them.

unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.
 2023-04-01 23:19:15 -04:00
comfyanonymous
2e73367f45 Merge T2IAdapterLoader and ControlNetLoader. 
Workflows will be auto updated.
 2023-03-17 18:17:59 -04:00
comfyanonymous
e1a9e26968 Add folder_paths so models can be in multiple paths. 2023-03-17 18:01:11 -04:00
comfyanonymous
494cfe5444 Prevent model_management from being loaded twice. 2023-03-15 15:18:18 -04:00
comfyanonymous
c8f1acc4eb Put image upscaling nodes in image/upscaling category. 2023-03-11 18:10:36 -05:00
comfyanonymous
9db2e97b47 Tiled upscaling with the upscale models. 2023-03-11 14:04:13 -05:00
comfyanonymous
905857edd8 Take some code from chainner to implement ESRGAN and other upscale models. 2023-03-11 13:09:28 -05:00
comfyanonymous
7ec1dd25a2 A tiny bit of reorganizing. 2023-03-06 01:30:17 -05:00
comfyanonymous
47acb3d73e Implement support for t2i style model. 
It needs the CLIPVision model so I added CLIPVisionLoader and CLIPVisionEncode.

Put the clip vision model in models/clip_vision
Put the t2i style model in models/style_models

StyleModelLoader to load it, StyleModelApply to apply it
ConditioningAppend to append the conditioning it outputs to a positive one.
 2023-03-05 18:39:25 -05:00