comfyanonymous
16eabdf70d
Free more vram for upscale models.
7 months ago
comfyanonymous
d09b5ef4ef
Free some memory before loading upscale models.
7 months ago
comfyanonymous
8be46438be
Support DiffBIR SwinIR models.
1 year ago
comfyanonymous
a51f33ee49
Use bigger tiles when upscaling with model and fallback on OOM.
1 year ago
comfyanonymous
587f89fe5a
Enable safe loading for upscale models.
2 years ago
comfyanonymous
fcf513e0b6
Refactor.
2 years ago
pythongosssss
5eeecf3fd5
remove unused import
2 years ago
pythongosssss
8912623ea9
use comfy progress bar
2 years ago
pythongosssss
06ad35b493
added progress to encode + upscale
2 years ago
comfyanonymous
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2 years ago
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.
2 years ago
comfyanonymous
2e73367f45
Merge T2IAdapterLoader and ControlNetLoader.
...
Workflows will be auto updated.
2 years ago
comfyanonymous
e1a9e26968
Add folder_paths so models can be in multiple paths.
2 years ago
comfyanonymous
494cfe5444
Prevent model_management from being loaded twice.
2 years ago
comfyanonymous
c8f1acc4eb
Put image upscaling nodes in image/upscaling category.
2 years ago
comfyanonymous
9db2e97b47
Tiled upscaling with the upscale models.
2 years ago
comfyanonymous
905857edd8
Take some code from chainner to implement ESRGAN and other upscale models.
2 years ago