.. |
cldm
|
Add manual cast to controlnet.
|
1 year ago |
extra_samplers
|
Cleanup uni_pc inpainting.
|
1 year ago |
k_diffusion
|
heunpp2 sampler.
|
1 year ago |
ldm
|
Move cascade scale factor from stage_a to latent_formats.py
|
11 months ago |
sd1_tokenizer
|
Initial commit.
|
2 years ago |
t2i_adapter
|
All resolutions now work with t2i adapter for SDXL.
|
2 years ago |
taesd
|
Fix taesd VAE in lowvram mode.
|
1 year ago |
checkpoint_pickle.py
|
Remove pytorch_lightning dependency.
|
2 years ago |
cli_args.py
|
Change log levels.
|
12 months ago |
clip_config_bigg.json
|
This is unused but it should be 1280.
|
2 years ago |
clip_model.py
|
Always return unprojected pooled output for gligen.
|
1 year ago |
clip_vision.py
|
Replace prints with logging and add --verbose argument.
|
12 months ago |
clip_vision_config_g.json
|
Add support for clip g vision model to CLIPVisionLoader.
|
2 years ago |
clip_vision_config_h.json
|
Add support for unCLIP SD2.x models.
|
2 years ago |
clip_vision_config_vitl.json
|
Add support for unCLIP SD2.x models.
|
2 years ago |
conds.py
|
Cleanup some unused imports.
|
1 year ago |
controlnet.py
|
Fix control loras breaking.
|
12 months ago |
diffusers_convert.py
|
Change log levels.
|
12 months ago |
diffusers_load.py
|
Cleanup some unused imports.
|
1 year ago |
gligen.py
|
Fix gligen lowvram mode.
|
1 year ago |
latent_formats.py
|
Move cascade scale factor from stage_a to latent_formats.py
|
11 months ago |
lora.py
|
Replace prints with logging and add --verbose argument.
|
12 months ago |
model_base.py
|
Change log levels.
|
12 months ago |
model_detection.py
|
Replace prints with logging and add --verbose argument.
|
12 months ago |
model_management.py
|
Lower memory usage for loras in lowvram mode at the cost of perf.
|
12 months ago |
model_patcher.py
|
Lower memory usage for loras in lowvram mode at the cost of perf.
|
12 months ago |
model_sampling.py
|
Remove useless check.
|
12 months ago |
ops.py
|
Fix control loras breaking.
|
12 months ago |
options.py
|
Only parse command line args when main.py is called.
|
1 year ago |
sample.py
|
Don't round noise mask.
|
1 year ago |
samplers.py
|
SamplerDPMAdaptative node to test the different options.
|
11 months ago |
sd.py
|
Change log levels.
|
12 months ago |
sd1_clip.py
|
Replace prints with logging and add --verbose argument.
|
12 months ago |
sd1_clip_config.json
|
Initial commit.
|
2 years ago |
sd2_clip.py
|
Cleaner CLIP text encoder implementation.
|
1 year ago |
sd2_clip_config.json
|
Move text_projection to base clip model.
|
2 years ago |
sdxl_clip.py
|
Always return unprojected pooled output for gligen.
|
1 year ago |
supported_models.py
|
Make saved SD1 checkpoints match more closely the official one.
|
11 months ago |
supported_models_base.py
|
Some cleanups to how the text encoders are loaded.
|
1 year ago |
utils.py
|
Change log levels.
|
12 months ago |