comfyanonymous
|
560e9f7a43
|
Disable repo owner validation in update.py
|
1 year ago |
comfyanonymous
|
b9818eb910
|
Add route to get safetensors metadata:
/view_metadata/loras?filename=lora.safetensors
|
1 year ago |
Dr.Lt.Data
|
23ffafeb5d
|
typo fix: field name in error message
|
1 year ago |
comfyanonymous
|
a532888846
|
Support VAEs in diffusers format.
|
1 year ago |
comfyanonymous
|
0fc483dcfd
|
Refactor diffusers model convert code to be able to reuse it.
|
1 year ago |
comfyanonymous
|
f3ac938b4a
|
Round the mask values for bitwise operations.
|
1 year ago |
comfyanonymous
|
ad81fd682a
|
Fix issue with cancelling prompt.
|
1 year ago |
comfyanonymous
|
1cfb2a733f
|
Merge branch 'error-improvements' of https://github.com/space-nuko/ComfyUI
|
1 year ago |
space-nuko
|
00646b0813
|
Bitwise operations for masks
|
1 year ago |
space-nuko
|
03f2d0a764
|
Rename exception message field
|
2 years ago |
space-nuko
|
52c9590b7b
|
Exception message
|
2 years ago |
space-nuko
|
62bdd9d26a
|
Catch typecast errors
|
2 years ago |
space-nuko
|
a9e7e23724
|
Fix
|
2 years ago |
space-nuko
|
e2d080b694
|
Return null for value format
|
2 years ago |
space-nuko
|
6b2a8a3845
|
Show message in the frontend if prompt execution raises an exception
|
2 years ago |
space-nuko
|
ffec815257
|
Send back more information about exceptions that happen during execution
|
2 years ago |
space-nuko
|
0d834e3a2b
|
Add missing input name/config
|
2 years ago |
space-nuko
|
c33b7c5549
|
Improve invalid prompt error message
|
2 years ago |
space-nuko
|
cc4d3435d3
|
Highlight failing nodes/inputs in frontend
|
2 years ago |
space-nuko
|
73e85fb3f4
|
Improve error output for failed nodes
|
2 years ago |
comfyanonymous
|
9144947244
|
Merge branch 'zero-lora-weights' of https://github.com/space-nuko/ComfyUI
|
2 years ago |
comfyanonymous
|
679bd2845a
|
Safetensors isn't optional anymore.
|
2 years ago |
space-nuko
|
4d1ed829d9
|
Don't load some model types if weight is zero
|
2 years ago |
comfyanonymous
|
eb4bd7711a
|
Remove einops.
|
2 years ago |
comfyanonymous
|
87ab25fac7
|
Do operations in same order as the one it replaces.
|
2 years ago |
comfyanonymous
|
2b1fac9708
|
Merge branch 'master' of https://github.com/BlenderNeko/ComfyUI
|
2 years ago |
comfyanonymous
|
e1278fa925
|
Support old pytorch versions that don't have weights_only.
|
2 years ago |
BlenderNeko
|
8b4b0c3188
|
vecorized bislerp
|
2 years ago |
comfyanonymous
|
9b1396e93a
|
Fix issue importing other ui prompts.
|
2 years ago |
comfyanonymous
|
7310290f17
|
Pull in latest upscale model code from chainner.
|
2 years ago |
comfyanonymous
|
c00bb1a0b7
|
Add a latent upscale by node.
|
2 years ago |
comfyanonymous
|
b8ccbec6d8
|
Various improvements to bislerp.
|
2 years ago |
comfyanonymous
|
451fb4169a
|
Fix 'git pull' not working on the standalones.
|
2 years ago |
comfyanonymous
|
34887b8885
|
Add experimental bislerp algorithm for latent upscaling.
It's like bilinear but with slerp.
|
2 years ago |
comfyanonymous
|
48fcc5b777
|
Parsing error crash.
|
2 years ago |
comfyanonymous
|
bfb13f5eee
|
Remove useless call to /object_info
|
2 years ago |
comfyanonymous
|
db27b0405a
|
object_info now returns if node is an output_node or not.
|
2 years ago |
comfyanonymous
|
ffc56c53c9
|
Add a node_errors to the /prompt error json response.
"node_errors" contains a dict keyed by node ids. The contents are a message
and a list of dependent outputs.
|
2 years ago |
comfyanonymous
|
6cc450579b
|
Auto transpose images from exif data.
|
2 years ago |
comfyanonymous
|
dc198650c0
|
sample_dpmpp_2m_sde no longer crashes when step == 1.
|
2 years ago |
comfyanonymous
|
4796e615dd
|
Revert DPI fix since it caused more issues than it solved.
|
2 years ago |
comfyanonymous
|
069657fbf3
|
Add DPM-Solver++(2M) SDE and exponential scheduler.
exponential scheduler is the one recommended with this sampler.
|
2 years ago |
comfyanonymous
|
516119ad83
|
Print min and max values in validation error message.
|
2 years ago |
comfyanonymous
|
3c76f43057
|
Cleaner code.
|
2 years ago |
comfyanonymous
|
b8636a44aa
|
Make scaled_dot_product switch to sliced attention on OOM.
|
2 years ago |
comfyanonymous
|
797c4e8d3b
|
Simplify and improve some vae attention code.
|
2 years ago |
comfyanonymous
|
71666f248f
|
Fix padding in Blur.
|
2 years ago |
BlenderNeko
|
36af98d755
|
improve sharpen and blur nodes
|
2 years ago |
comfyanonymous
|
b9daf4e30f
|
Add a /object_info/{node_class} route to get only the info of one node.
|
2 years ago |
malern
|
e6e1999f96
|
Render UI at a higher resolution when viewing with a higher pixel ratio
|
2 years ago |