| .. |
|
cldm
|
Refactor code so model can be a dtype other than fp32 or fp16.
|
1 year ago |
|
extra_samplers
|
Fix uni_pc returning noisy image when steps <= 3
|
1 year ago |
|
k_diffusion
|
Fix uni_pc sampler math. This changes the images this sampler produces.
|
1 year ago |
|
ldm
|
attention_basic now works with hypertile.
|
1 year ago |
|
sd1_tokenizer
|
Initial commit.
|
2 years ago |
|
t2i_adapter
|
All resolutions now work with t2i adapter for SDXL.
|
1 year ago |
|
taesd
|
Cleanup.
|
1 year ago |
|
checkpoint_pickle.py
|
Remove pytorch_lightning dependency.
|
1 year ago |
|
cli_args.py
|
Add a --bf16-unet to test running the unet in bf16.
|
1 year ago |
|
clip_config_bigg.json
|
This is unused but it should be 1280.
|
1 year ago |
|
clip_vision.py
|
Fix some potential issues.
|
1 year ago |
|
clip_vision_config_g.json
|
Add support for clip g vision model to CLIPVisionLoader.
|
1 year 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
|
Refactor to make it easier to add custom conds to models.
|
1 year ago |
|
controlnet.py
|
change 'c_adm' to 'y' in ControlNet.get_control
|
1 year ago |
|
diffusers_convert.py
|
Fix diffusers VAE loading.
|
1 year ago |
|
diffusers_load.py
|
Make VAE code closer to sgm.
|
1 year ago |
|
gligen.py
|
Smarter memory management.
|
1 year ago |
|
latent_formats.py
|
Supports TAESD models in safetensors format
|
1 year ago |
|
lora.py
|
Implement loras with norm keys.
|
1 year ago |
|
model_base.py
|
Pass extra conds directly to unet.
|
1 year ago |
|
model_detection.py
|
Refactor code so model can be a dtype other than fp32 or fp16.
|
1 year ago |
|
model_management.py
|
Empty the cache when torch cache is more than 25% free mem.
|
1 year ago |
|
model_patcher.py
|
Let unet wrapper functions have .to attributes.
|
1 year ago |
|
ops.py
|
Initialize text encoder to target dtype.
|
1 year ago |
|
options.py
|
Only parse command line args when main.py is called.
|
1 year ago |
|
sample.py
|
Refactor to make it easier to add custom conds to models.
|
1 year ago |
|
samplers.py
|
Refactor to make it easier to add custom conds to models.
|
1 year ago |
|
sd.py
|
Fix some potential issues.
|
1 year ago |
|
sd1_clip.py
|
Support for text encoder models that need attention_mask.
|
1 year ago |
|
sd1_clip_config.json
|
Initial commit.
|
2 years ago |
|
sd2_clip.py
|
Set last layer on SD2.x models uses the proper indexes now.
|
1 year ago |
|
sd2_clip_config.json
|
Move text_projection to base clip model.
|
1 year ago |
|
sdxl_clip.py
|
Move text_projection to base clip model.
|
1 year ago |
|
supported_models.py
|
Move some functions to utils.py
|
1 year ago |
|
supported_models_base.py
|
Move some functions to utils.py
|
1 year ago |
|
utils.py
|
Make VAE code closer to sgm.
|
1 year ago |
comfyanonymous