| .. |
|
cldm
|
Add manual cast to controlnet.
|
1 year ago |
|
extra_samplers
|
Remove useless argument from uni_pc sampler.
|
1 year ago |
|
k_diffusion
|
heunpp2 sampler.
|
1 year ago |
|
ldm
|
Use basic attention implementation for small inputs on old pytorch.
|
1 year 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
|
Store user settings/data on the server and multi user support (#2160)
|
1 year ago |
|
clip_config_bigg.json
|
This is unused but it should be 1280.
|
2 years ago |
|
clip_model.py
|
Update optimized_attention_for_device function for new functions that
|
1 year ago |
|
clip_vision.py
|
Don't resize clip vision image when the size is already good.
|
1 year 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
|
Add a CONDConstant for passing non tensor conds to unet.
|
1 year ago |
|
controlnet.py
|
Fix issue when using multiple t2i adapters with batched images.
|
1 year ago |
|
diffusers_convert.py
|
Fix diffusers VAE loading.
|
2 years ago |
|
diffusers_load.py
|
Make VAE code closer to sgm.
|
1 year ago |
|
gligen.py
|
Smarter memory management.
|
2 years ago |
|
latent_formats.py
|
Add support for the stable diffusion x4 upscaling model.
|
1 year ago |
|
lora.py
|
Implement GLora.
|
1 year ago |
|
model_base.py
|
Implement noise augmentation for SD 4X upscale model.
|
1 year ago |
|
model_detection.py
|
Fix regression.
|
1 year ago |
|
model_management.py
|
Add argument to run the VAE on the CPU.
|
1 year ago |
|
model_patcher.py
|
Fix model patches not working in custom sampling scheduler nodes.
|
1 year ago |
|
model_sampling.py
|
Add linear_start and linear_end to model_config.sampling_settings
|
1 year ago |
|
ops.py
|
Greatly improve lowvram sampling speed by getting rid of accelerate.
|
1 year ago |
|
options.py
|
Only parse command line args when main.py is called.
|
1 year ago |
|
sample.py
|
Support stable zero 123 model.
|
1 year ago |
|
samplers.py
|
Implement noise augmentation for SD 4X upscale model.
|
1 year ago |
|
sd.py
|
Add support for the stable diffusion x4 upscaling model.
|
1 year ago |
|
sd1_clip.py
|
Switch text encoder to manual cast.
|
1 year 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
|
Cleaner CLIP text encoder implementation.
|
1 year ago |
|
supported_models.py
|
Implement noise augmentation for SD 4X upscale model.
|
1 year ago |
|
supported_models_base.py
|
Use faster manual cast for fp8 in unet.
|
1 year ago |
|
utils.py
|
Make --gpu-only put intermediate values in GPU memory instead of cpu.
|
1 year ago |
