comfyanonymous b2f03164c7 Prevent the clip_g position_ids key from being saved in the checkpoint. ...

This is to make it match the official checkpoint.

2023-07-12 20:15:02 -04:00

..

cldm

Support base SDXL and SDXL refiner models.

2023-06-22 13:03:50 -04:00

extra_samplers

Add a total_steps value to sampler callback.

2023-05-03 12:58:10 -04:00

k_diffusion

Add gpu variations of the sde samplers that are less deterministic

2023-07-05 01:39:38 -04:00

ldm

Disable autocast in unet for increased speed.

2023-07-05 21:58:29 -04:00

sd1_tokenizer

Initial commit.

2023-01-16 22:37:14 -05:00

t2i_adapter

Make t2i adapter work with any latent resolution.

2023-05-08 18:15:19 -04:00

taesd

Refactor previews into one command line argument.

2023-06-06 02:13:05 -04:00

checkpoint_pickle.py

Remove pytorch_lightning dependency.

2023-06-13 10:11:33 -04:00

cli_args.py

Add arguments to run the VAE in fp16 or bf16 for testing.

2023-07-06 23:23:46 -04:00

clip_config_bigg.json

This is unused but it should be 1280.

2023-06-28 18:04:23 -04:00

clip_vision_config_h.json

Add support for unCLIP SD2.x models.

2023-04-01 23:19:15 -04:00

clip_vision_config_vitl.json

Add support for unCLIP SD2.x models.

2023-04-01 23:19:15 -04:00

clip_vision.py

Fix error with ClipVision loader node.

2023-06-23 01:08:05 -04:00

diffusers_convert.py

Add CheckpointSave node to save checkpoints.

2023-06-26 12:22:27 -04:00

diffusers_load.py

Support loading unet files in diffusers format.

2023-07-05 17:38:59 -04:00

gligen.py

Disable autocast in unet for increased speed.

2023-07-05 21:58:29 -04:00

latent_formats.py

Support SDXL embedding format with 2 CLIP.

2023-07-10 10:34:59 -04:00

model_base.py

Disable autocast in unet for increased speed.

2023-07-05 21:58:29 -04:00

model_detection.py

Support loading unet files in diffusers format.

2023-07-05 17:38:59 -04:00

model_management.py

Empty cache after model unloading for normal vram and lower.

2023-07-09 09:56:03 -04:00

ops.py

Properly disable weight initialization in clip models.

2023-06-14 20:13:08 -04:00

sample.py

Disable autocast in unet for increased speed.

2023-07-05 21:58:29 -04:00

samplers.py

Merge branch 'condmask-fix' of https://github.com/vmedea/ComfyUI

2023-07-07 01:52:25 -04:00

sd1_clip_config.json

Initial commit.

2023-01-16 22:37:14 -05:00

sd1_clip.py

Fix potential tensors being on different devices issues.

2023-07-12 19:29:27 -04:00

sd2_clip_config.json

Use transformers CLIP instead of open_clip for SD2.x

2023-02-05 14:36:28 -05:00

sd2_clip.py

Allow passing custom path to clip-g and clip-h.

2023-07-03 15:45:04 -04:00

sd.py

Don't patch weights when multiplier is zero.

2023-07-09 17:46:56 -04:00

sdxl_clip.py

Support SDXL embedding format with 2 CLIP.

2023-07-10 10:34:59 -04:00

supported_models_base.py

Support loading unet files in diffusers format.

2023-07-05 17:38:59 -04:00

supported_models.py

Prevent the clip_g position_ids key from being saved in the checkpoint.

2023-07-12 20:15:02 -04:00

utils.py

Fix loras not working when loading checkpoint with config.

2023-07-05 19:42:24 -04:00