| .. |
|
cldm
|
Support AliMama SD3 and Flux inpaint controlnets.
|
2024-09-14 09:05:16 -04:00 |
|
extra_samplers
|
Cleanup uni_pc inpainting.
|
2024-02-23 02:39:35 -05:00 |
|
k_diffusion
|
Add dpmpp_2m_cfg_pp (#4992)
|
2024-09-24 02:42:56 -04:00 |
|
ldm
|
Allow using SD3 type te output on flux model.
|
2024-10-03 09:44:54 -04:00 |
|
sd1_tokenizer
|
…
|
|
|
t2i_adapter
|
…
|
|
|
taesd
|
…
|
|
|
text_encoders
|
Make clip loader nodes support loading sd3 t5xxl in lower precision.
|
2024-10-10 15:06:15 -04:00 |
|
checkpoint_pickle.py
|
…
|
|
|
cli_args.py
|
Let --verbose have an argument for the log level.
|
2024-10-04 10:05:34 -04:00 |
|
clip_config_bigg.json
|
…
|
|
|
clip_model.py
|
Support loading long clipl model with the CLIP loader node.
|
2024-08-20 10:46:36 -04:00 |
|
clip_vision.py
|
Some minor cleanups.
|
2024-10-05 13:22:39 -04:00 |
|
clip_vision_config_g.json
|
…
|
|
|
clip_vision_config_h.json
|
…
|
|
|
clip_vision_config_vitl.json
|
…
|
|
|
clip_vision_config_vitl_336.json
|
…
|
|
|
comfy_types.py
|
types -> comfy_types to fix import issue.
|
2024-09-12 03:57:46 -04:00 |
|
conds.py
|
…
|
|
|
controlnet.py
|
🐛 Add device to variable c (#5210)
|
2024-10-11 20:37:50 -04:00 |
|
diffusers_convert.py
|
…
|
|
|
diffusers_load.py
|
load_unet -> load_diffusion_model with a model_options argument.
|
2024-08-12 23:20:57 -04:00 |
|
float.py
|
Some minor cleanups.
|
2024-10-05 13:22:39 -04:00 |
|
gligen.py
|
…
|
|
|
latent_formats.py
|
Make SD3 fast previews a little better.
|
2024-10-07 09:19:59 -04:00 |
|
lora.py
|
Fix flux doras with diffusers keys.
|
2024-10-08 19:03:40 -04:00 |
|
model_base.py
|
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
|
2024-10-09 19:43:17 -04:00 |
|
model_detection.py
|
Added SD15_Inpaint_Diffusers model support for unet_config_from_diffusers_unet function (#4565)
|
2024-08-23 03:57:08 -04:00 |
|
model_management.py
|
Increase maximum macOS version to 15.0.1 when forcing upcast attention (#5191)
|
2024-10-09 22:21:41 -04:00 |
|
model_patcher.py
|
Fix issue with loras, lowvram and --fast fp8.
|
2024-09-28 14:42:32 -04:00 |
|
model_sampling.py
|
Basic Flux Schnell and Flux Dev model implementation.
|
2024-08-01 09:49:29 -04:00 |
|
ops.py
|
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
|
2024-10-09 19:43:17 -04:00 |
|
options.py
|
…
|
|
|
sample.py
|
…
|
|
|
sampler_helpers.py
|
Make ComfyUI split batches a higher priority than weight offload.
|
2024-08-01 16:39:59 -04:00 |
|
samplers.py
|
Add dpmpp_2m_cfg_pp (#4992)
|
2024-09-24 02:42:56 -04:00 |
|
sd.py
|
model_options consistency between functions.
|
2024-10-11 20:51:19 -04:00 |
|
sd1_clip.py
|
Long CLIP L support for SDXL, SD3 and Flux.
|
2024-09-15 07:59:38 -04:00 |
|
sd1_clip_config.json
|
…
|
|
|
sdxl_clip.py
|
Long CLIP L support for SDXL, SD3 and Flux.
|
2024-09-15 07:59:38 -04:00 |
|
supported_models.py
|
Fix issue.
|
2024-08-22 10:38:24 -04:00 |
|
supported_models_base.py
|
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
|
2024-10-09 19:43:17 -04:00 |
|
utils.py
|
Improve tiling calculations to reduce number of tiles that need to be processed. (#4944)
|
2024-09-17 03:51:10 -04:00 |
6632365e16