| .. |
|
cldm
|
Remove autocast from controlnet code.
|
1 year ago |
|
extra_samplers
|
fix: typo in extra sampler
|
1 year ago |
|
k_diffusion
|
Add DDPM sampler.
|
1 year ago |
|
ldm
|
Model patches can now know which batch is positive and negative.
|
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
|
Refactor previews into one command line argument.
|
1 year ago |
|
checkpoint_pickle.py
|
Remove pytorch_lightning dependency.
|
1 year ago |
|
cli_args.py
|
Only parse command line args when main.py is called.
|
1 year ago |
|
clip_config_bigg.json
|
This is unused but it should be 1280.
|
1 year ago |
|
clip_vision.py
|
Don't leave very large hidden states in the clip vision output.
|
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 |
|
controlnet.py
|
Support more controlnet models.
|
1 year ago |
|
diffusers_convert.py
|
Fix diffusers VAE loading.
|
1 year ago |
|
diffusers_load.py
|
Clean up DiffusersLoader node.
|
1 year ago |
|
gligen.py
|
Smarter memory management.
|
1 year ago |
|
latent_formats.py
|
Support models without previews.
|
1 year ago |
|
lora.py
|
Implement loras with norm keys.
|
1 year ago |
|
model_base.py
|
Allow having a different pooled output for each image in a batch.
|
1 year ago |
|
model_detection.py
|
Support more controlnet models.
|
1 year ago |
|
model_management.py
|
Allow Intel GPUs to LoRA cast on GPU since it supports BF16 natively.
|
1 year ago |
|
model_patcher.py
|
Add a way to set output block patches to modify the h and hsp.
|
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
|
Add a SamplerCustom Node.
|
1 year ago |
|
samplers.py
|
Add SamplerDPMPP_2M_SDE node.
|
1 year ago |
|
sd.py
|
load_checkpoint_guess_config can now optionally output the model.
|
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
|
Don't depend on torchvision.
|
1 year ago |
comfyanonymous