comfyanonymous
de142eaad5
Simpler base model code.
1 year ago
comfyanonymous
0e425603fb
Small refactor.
1 year ago
comfyanonymous
700491d81a
Implement global average pooling for controlnet.
1 year ago
comfyanonymous
03da8a3426
This is useless for inference.
1 year ago
comfyanonymous
eb448dd8e1
Auto load model in lowvram if not enough memory.
1 year ago
comfyanonymous
a532888846
Support VAEs in diffusers format.
2 years ago
BlenderNeko
19c014f429
comment out annoying print statement
2 years ago
BlenderNeko
d9e088ddfd
minor changes for tiled sampler
2 years ago
comfyanonymous
bae4fb4a9d
Fix imports.
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
27df74101e
reduce duplication
2 years ago
pythongosssss
06ad35b493
added progress to encode + upscale
2 years ago
comfyanonymous
9c335a553f
LoKR support.
2 years ago
pythongosssss
c8c9926eeb
Add progress to vae decode tiled
2 years ago
comfyanonymous
5282f56434
Implement Linear hypernetworks.
...
Add a HypernetworkLoader node to use hypernetworks.
2 years ago
comfyanonymous
3696d1699a
Add support for GLIGEN textbox model.
2 years ago
comfyanonymous
884ea653c8
Add a way for nodes to set a custom CFG function.
2 years ago
comfyanonymous
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2 years ago
comfyanonymous
81d1f00df3
Some refactoring: from_tokens -> encode_from_tokens
2 years ago
BlenderNeko
da115bd78d
ensure backwards compat with optional args
2 years ago
BlenderNeko
73175cf58c
split tokenizer from encoder
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
18a6c1db33
Add a TomePatchModel node to the _for_testing section.
...
Tome increases sampling speed at the expense of quality.
2 years ago
comfyanonymous
b2554bc4dd
Split VAE decode batches depending on free memory.
2 years ago
comfyanonymous
dd095efc2c
Support loha that use cp decomposition.
2 years ago
comfyanonymous
94a7c895f4
Add loha support.
2 years ago
comfyanonymous
3ed4a4e4e6
Try again with vae tiled decoding if regular fails because of OOM.
2 years ago
comfyanonymous
4039616ca6
Less seams in tiled outputs at the cost of more processing.
2 years ago
comfyanonymous
cc309568e1
Add support for locon mid weights.
2 years ago
comfyanonymous
edfc4ca663
Try to fix a vram issue with controlnets.
2 years ago
comfyanonymous
2e73367f45
Merge T2IAdapterLoader and ControlNetLoader.
...
Workflows will be auto updated.
2 years ago
comfyanonymous
0e836d525e
use half() on fp16 models loaded with config.
2 years ago
comfyanonymous
986dd820dc
Use half() function on model when loading in fp16.
2 years ago
comfyanonymous
54dbfaf2ec
Remove omegaconf dependency and some ci changes.
2 years ago
comfyanonymous
e33dc2b33b
Add a VAEEncodeTiled node.
2 years ago
comfyanonymous
9db2e97b47
Tiled upscaling with the upscale models.
2 years ago
comfyanonymous
cd64111c83
Add locon support.
2 years ago
comfyanonymous
c70f0ac64b
SD2.x controlnets now work.
2 years ago
comfyanonymous
19415c3ace
Relative imports to test something.
2 years ago
comfyanonymous
501f19eec6
Fix clip_skip no longer being loaded from yaml file.
2 years ago
comfyanonymous
afff30fc0a
Add --cpu to use the cpu for inference.
2 years ago
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.
2 years ago
comfyanonymous
16130c7546
Add support for new colour T2I adapter model.
2 years ago
comfyanonymous
4215206281
Add a node to set CLIP skip.
...
Use a more simple way to detect if the model is -v prediction.
2 years ago
comfyanonymous
fed315a76a
To be really simple CheckpointLoaderSimple should pick the right type.
2 years ago
comfyanonymous
94bb0375b0
New CheckpointLoaderSimple to load checkpoints without a config.
2 years ago
comfyanonymous
b31daadc03
Try to improve memory issues with del.
2 years ago
comfyanonymous
9f4214e534
Preparing to add another function to load checkpoints.
2 years ago