qnloft
/
ComfyUI
mirror of https://github.com/comfyanonymous/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
ComfyUI/comfy
History
Rafie Walker 6761233e9d
Implement Self-Attention Guidance (#2201) 
* First SAG test

* need to put extra options on the model instead of patcher

* no errors and results seem not-broken

* Use @ashen-uncensored formula, which works better!!!

* Fix a crash when using weird resolutions. Remove an unnecessary UNet call

* Improve comments, optimize memory in blur routine

* SAG works with sampler_cfg_function
 		2023-12-13 15:52:11 -05:00
..
cldm Add manual cast to controlnet. 2023-12-12 11:32:42 -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 Refactor comfy.ops 2023-12-11 23:27:13 -05:00
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 Add taesd and taesdxl to VAELoader node. 2023-11-21 12:54:19 -05:00
checkpoint_pickle.py Remove pytorch_lightning dependency. 2023-06-13 10:11:33 -04:00
cli_args.py Add an option --fp16-unet to force using fp16 for the unet. 2023-12-11 18:36:29 -05:00
clip_config_bigg.json This is unused but it should be 1280. 2023-06-28 18:04:23 -04:00
clip_model.py Use own clip vision model implementation. 2023-12-09 11:56:31 -05:00
clip_vision.py Refactor comfy.ops 2023-12-11 23:27:13 -05:00
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
conds.py Add a CONDConstant for passing non tensor conds to unet. 2023-11-08 01:59:09 -05:00
controlnet.py Add manual cast to controlnet. 2023-12-12 11:32:42 -05:00
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 Implement GLora. 2023-12-09 18:15:26 -05:00
model_base.py Use inference dtype for unet memory usage estimation. 2023-12-11 23:50:38 -05:00
model_detection.py Support segmind vega model. 2023-12-12 19:09:53 -05:00
model_management.py Add an option --fp16-unet to force using fp16 for the unet. 2023-12-11 18:36:29 -05:00
model_patcher.py Implement GLora. 2023-12-09 18:15:26 -05:00
model_sampling.py Add linear_start and linear_end to model_config.sampling_settings 2023-12-08 02:49:30 -05:00
ops.py Refactor comfy.ops 2023-12-11 23:27:13 -05:00
options.py Only parse command line args when main.py is called. 2023-09-13 11:38:20 -04:00
sample.py Make --gpu-only put intermediate values in GPU memory instead of cpu. 2023-12-08 02:35:45 -05:00
samplers.py Implement Self-Attention Guidance (#2201) 2023-12-13 15:52:11 -05:00
sd.py Add dtype parameter to VAE object. 2023-12-12 12:03:29 -05:00
sd1_clip.py Switch text encoder to manual cast. 2023-12-10 23:00:54 -05:00
sd1_clip_config.json Initial commit. 2023-01-16 22:37:14 -05:00
sd2_clip.py Cleaner CLIP text encoder implementation. 2023-12-06 23:50:03 -05:00
sd2_clip_config.json Move text_projection to base clip model. 2023-08-24 23:43:48 -04:00
sdxl_clip.py Cleaner CLIP text encoder implementation. 2023-12-06 23:50:03 -05:00
supported_models.py Support segmind vega model. 2023-12-12 19:09:53 -05:00
supported_models_base.py Use faster manual cast for fp8 in unet. 2023-12-11 18:24:44 -05:00
utils.py Make --gpu-only put intermediate values in GPU memory instead of cpu. 2023-12-08 02:35:45 -05:00