The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
comfyanonymous ef815ba1e2 Switch default scheduler to normal. 2 years ago
..
cldm Fix imports. 2 years ago
extra_samplers Add a total_steps value to sampler callback. 2 years ago
k_diffusion Add some low vram modes: --lowvram and --novram 2 years ago
ldm minor changes for tiled sampler 2 years ago
sd1_tokenizer Initial commit. 2 years ago
t2i_adapter Make t2i adapter work with any latent resolution. 2 years ago
cli_args.py auto-launch cli arg 2 years ago
clip_vision.py Fix for new transformers version. 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
diffusers_convert.py Cleanup. 2 years ago
gligen.py Lowvram mode for gligen and fix some lowvram issues. 2 years ago
model_management.py Print the torch device that is used on startup. 2 years ago
sample.py Make nodes map over input lists (#579) 2 years ago
samplers.py Switch default scheduler to normal. 2 years ago
sd.py comment out annoying print statement 2 years ago
sd1_clip.py Search recursively in subfolders for embeddings. 2 years ago
sd1_clip_config.json Initial commit. 2 years ago
sd2_clip.py Some refactoring: from_tokens -> encode_from_tokens 2 years ago
sd2_clip_config.json Use transformers CLIP instead of open_clip for SD2.x 2 years ago
utils.py Refactor. 2 years ago