| .. |
|
cldm
|
Remove useless code.
|
8 months ago |
|
extra_samplers
|
Cleanup uni_pc inpainting.
|
1 year ago |
|
k_diffusion
|
Switch to the real cfg++ method in the samplers.
|
8 months ago |
|
ldm
|
Basic SD3 controlnet implementation.
|
8 months ago |
|
sd1_tokenizer
|
Initial commit.
|
2 years ago |
|
t2i_adapter
|
Controlnet refactor.
|
8 months ago |
|
t5_tokenizer
|
SD3 Support.
|
9 months ago |
|
taesd
|
Improvements to the TAESD3 implementation.
|
8 months ago |
|
checkpoint_pickle.py
|
Remove pytorch_lightning dependency.
|
2 years ago |
|
cli_args.py
|
Add `--no-custom-node` cmd flag (#3903)
|
8 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
|
Fix bug with cosxl edit model.
|
9 months ago |
|
controlnet.py
|
ControlNetApplySD3 node can now be used to use SD3 controlnets.
|
8 months ago |
|
diffusers_convert.py
|
Fix saving text encoder in fp8.
|
11 months ago |
|
diffusers_load.py
|
Cleanup some unused imports.
|
1 year ago |
|
gligen.py
|
Fix gligen lowvram mode.
|
1 year ago |
|
latent_formats.py
|
support TAESD3 (#3738)
|
8 months ago |
|
lora.py
|
Support OneTrainer SD3 lora format.
|
8 months ago |
|
model_base.py
|
Support saving stable audio checkpoint that can be loaded back.
|
8 months ago |
|
model_detection.py
|
Basic SD3 controlnet implementation.
|
8 months ago |
|
model_management.py
|
Use fp16 as the default vae dtype for the audio VAE.
|
8 months ago |
|
model_patcher.py
|
Add SamplerEulerCFG++ node.
|
8 months ago |
|
model_sampling.py
|
Add a way to set the timestep multiplier in the flow sampling.
|
8 months ago |
|
ops.py
|
Initial support for the stable audio open model.
|
8 months ago |
|
options.py
|
Only parse command line args when main.py is called.
|
1 year ago |
|
sa_t5.py
|
Initial support for the stable audio open model.
|
8 months ago |
|
sample.py
|
Reshape the empty latent image to the right amount of channels if needed.
|
9 months ago |
|
sampler_helpers.py
|
Refactor sampler code for more advanced sampler nodes part 2.
|
11 months ago |
|
samplers.py
|
Switch to the real cfg++ method in the samplers.
|
8 months ago |
|
sd.py
|
Better T5xxl detection.
|
8 months ago |
|
sd1_clip.py
|
Allow specifying the padding token for the tokenizer.
|
8 months ago |
|
sd1_clip_config.json
|
Initial commit.
|
2 years ago |
|
sd2_clip.py
|
Remove some unused imports.
|
9 months ago |
|
sd2_clip_config.json
|
Move text_projection to base clip model.
|
2 years ago |
|
sd3_clip.py
|
Single and dual clip loader nodes support SD3.
|
9 months ago |
|
sdxl_clip.py
|
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
|
9 months ago |
|
supported_models.py
|
Support saving stable audio checkpoint that can be loaded back.
|
8 months ago |
|
supported_models_base.py
|
Fix issue with sampling_settings persisting across models.
|
11 months ago |
|
t5.py
|
Support other types of T5 models.
|
8 months ago |
|
t5_config_base.json
|
Cleanup T5 code a bit.
|
8 months ago |
|
t5_config_xxl.json
|
Cleanup T5 code a bit.
|
8 months ago |
|
types.py
|
Fix UnetParams annotation typo (#3589)
|
9 months ago |
|
utils.py
|
Basic SD3 controlnet implementation.
|
8 months ago |
2dc84d1444