| .. |
|
cldm
|
UNET weights can now be stored in fp8.
|
2023-12-04 11:10:00 -05:00 |
|
extra_samplers
|
Remove useless argument from uni_pc sampler.
|
2023-11-12 01:25:33 -05:00 |
|
k_diffusion
|
heunpp2 sampler.
|
2023-11-14 23:50:55 -05:00 |
|
ldm
|
UNET weights can now be stored in fp8.
|
2023-12-04 11:10:00 -05:00 |
|
sd1_tokenizer
|
…
|
|
|
t2i_adapter
|
…
|
|
|
taesd
|
Add taesd and taesdxl to VAELoader node.
|
2023-11-21 12:54:19 -05:00 |
|
checkpoint_pickle.py
|
…
|
|
|
cli_args.py
|
UNET weights can now be stored in fp8.
|
2023-12-04 11:10:00 -05:00 |
|
clip_config_bigg.json
|
…
|
|
|
clip_vision.py
|
Faster clip image processing.
|
2023-10-26 01:53:01 -04:00 |
|
clip_vision_config_g.json
|
…
|
|
|
clip_vision_config_h.json
|
…
|
|
|
clip_vision_config_vitl.json
|
…
|
|
|
conds.py
|
Add a CONDConstant for passing non tensor conds to unet.
|
2023-11-08 01:59:09 -05:00 |
|
controlnet.py
|
Fix control lora on fp8.
|
2023-12-04 13:47:41 -05:00 |
|
diffusers_convert.py
|
…
|
|
|
diffusers_load.py
|
Make VAE code closer to sgm.
|
2023-10-17 15:18:51 -04:00 |
|
gligen.py
|
…
|
|
|
latent_formats.py
|
Supports TAESD models in safetensors format
|
2023-10-10 13:21:44 +09:00 |
|
lora.py
|
Add support for full diff lora keys.
|
2023-11-08 22:05:31 -05:00 |
|
model_base.py
|
UNET weights can now be stored in fp8.
|
2023-12-04 11:10:00 -05:00 |
|
model_detection.py
|
Fix importing diffusers unets.
|
2023-11-24 20:35:29 -05:00 |
|
model_management.py
|
Use .itemsize to get dtype size for fp8.
|
2023-12-04 11:52:06 -05:00 |
|
model_patcher.py
|
Make deep shrink behave like it should.
|
2023-11-16 15:26:28 -05:00 |
|
model_sampling.py
|
.sigma and .timestep now return tensors on the same device as the input.
|
2023-11-27 16:41:33 -05:00 |
|
ops.py
|
All the unet ops with weights are now handled by comfy.ops
|
2023-12-04 03:12:18 -05:00 |
|
options.py
|
Only parse command line args when main.py is called.
|
2023-09-13 11:38:20 -04:00 |
|
sample.py
|
Try to free memory for both cond+uncond before inference.
|
2023-11-27 14:55:40 -05:00 |
|
samplers.py
|
Invert the start and end percentages in the code.
|
2023-11-16 04:23:44 -05:00 |
|
sd.py
|
Use smart model management for VAE to decrease latency.
|
2023-11-28 04:58:51 -05:00 |
|
sd1_clip.py
|
Less useless downcasting.
|
2023-12-04 12:53:46 -05:00 |
|
sd1_clip_config.json
|
…
|
|
|
sd2_clip.py
|
CLIP code refactor and improvements.
|
2023-11-06 14:17:41 -05:00 |
|
sd2_clip_config.json
|
…
|
|
|
sdxl_clip.py
|
CLIP code refactor and improvements.
|
2023-11-06 14:17:41 -05:00 |
|
supported_models.py
|
Support SD2.1 turbo checkpoint.
|
2023-11-30 19:27:03 -05:00 |
|
supported_models_base.py
|
Add sampling_settings so models can specify specific sampling settings.
|
2023-11-22 17:24:00 -05:00 |
|
utils.py
|
A different way of handling multiple images passed to SVD.
|
2023-12-03 03:31:47 -05:00 |
26b1c0a771