comfyanonymous 656c0b5d90 CLIP code refactor and improvements. ...

More generic clip model class that can be used on more types of text
encoders.

Don't apply weighting algorithm when weight is 1.0

Don't compute an empty token output when it's not needed.

2023-11-06 14:17:41 -05:00

..

cldm

Support SSD1B model and make it easier to support asymmetric unets.

2023-10-27 14:45:15 -04:00

extra_samplers

Sampling code changes.

2023-10-31 17:33:43 -04:00

k_diffusion

Not used anymore.

2023-11-01 00:01:30 -04:00

ldm

Remove a bunch of useless code.

2023-10-31 18:11:29 -04:00

sd1_tokenizer

Initial commit.

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

t2i_adapter

All resolutions now work with t2i adapter for SDXL.

2023-08-22 16:23:54 -04:00

taesd

Cleanup.

2023-10-10 21:46:53 -04:00

checkpoint_pickle.py

Remove pytorch_lightning dependency.

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

cli_args.py

Add --max-upload-size argument, the default is 100MB.

2023-10-29 03:55:46 -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_g.json

Add support for clip g vision model to CLIPVisionLoader.

2023-08-18 11:13:29 -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

Faster clip image processing.

2023-10-26 01:53:01 -04:00

conds.py

Refactor to make it easier to add custom conds to models.

2023-10-24 23:31:12 -04:00

controlnet.py

Clean up percent start/end and make controlnets work with sigmas.

2023-10-31 22:14:32 -04:00

diffusers_convert.py

Fix diffusers VAE loading.

2023-07-26 18:26:39 -04:00

diffusers_load.py

Make VAE code closer to sgm.

2023-10-17 15:18:51 -04:00

gligen.py

Smarter memory management.

2023-08-17 01:06:34 -04:00

latent_formats.py

Supports TAESD models in safetensors format

2023-10-10 13:21:44 +09:00

lora.py

SD1 and SD2 clip and tokenizer code is now more similar to the SDXL one.

2023-10-27 15:54:04 -04:00

model_base.py

Move model sampling code to comfy/model_sampling.py

2023-11-04 01:32:23 -04:00

model_detection.py

Support SSD1B model and make it easier to support asymmetric unets.

2023-10-27 14:45:15 -04:00

model_management.py

Empty the cache when torch cache is more than 25% free mem.

2023-10-22 13:58:12 -04:00

model_patcher.py

fix unet_wrapper_function name in ModelPatcher

2023-11-05 17:11:44 +08:00

model_sampling.py

Move model sampling code to comfy/model_sampling.py

2023-11-04 01:32:23 -04:00

ops.py

Initialize text encoder to target dtype.

2023-08-23 21:01:15 -04:00

options.py

Only parse command line args when main.py is called.

2023-09-13 11:38:20 -04:00

sample.py

Refactor to make it easier to add custom conds to models.

2023-10-24 23:31:12 -04:00

samplers.py

Don't convert Nan to zero.

2023-11-03 13:13:15 -04:00

sd1_clip_config.json

Initial commit.

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

sd1_clip.py

CLIP code refactor and improvements.

2023-11-06 14:17:41 -05:00

sd2_clip_config.json

Move text_projection to base clip model.

2023-08-24 23:43:48 -04:00

sd2_clip.py

CLIP code refactor and improvements.

2023-11-06 14:17:41 -05:00

sd.py

Allow model or clip to be None in load_lora_for_models.

2023-11-01 20:27:20 -04:00

sdxl_clip.py

CLIP code refactor and improvements.

2023-11-06 14:17:41 -05:00

supported_models_base.py

Move some functions to utils.py

2023-09-02 22:33:37 -04:00

supported_models.py

SD1 and SD2 clip and tokenizer code is now more similar to the SDXL one.

2023-10-27 15:54:04 -04:00

utils.py

Support SSD1B model and make it easier to support asymmetric unets.

2023-10-27 14:45:15 -04:00