comfyanonymous
|
b3e97fc714
|
Koala 700M and 1B support.
Use the UNET Loader node to load the unet file to use them.
|
1 year ago |
|
comfyanonymous
|
37a86e4618
|
Remove duplicate text_projection key from some saved models.
|
1 year ago |
|
comfyanonymous
|
8daedc5bf2
|
Auto detect playground v2.5 model.
|
1 year ago |
|
comfyanonymous
|
d46583ecec
|
Playground V2.5 support with ModelSamplingContinuousEDM node.
Use ModelSamplingContinuousEDM with edm_playground_v2.5 selected.
|
1 year ago |
|
comfyanonymous
|
1e0fcc9a65
|
Make XL checkpoints save in a more standard format.
|
1 year ago |
|
comfyanonymous
|
b416be7d78
|
Make the text projection saved in the checkpoint the right format.
|
1 year ago |
|
comfyanonymous
|
03c47fc0f2
|
Add a min_length property to tokenizer class.
|
1 year ago |
|
comfyanonymous
|
8ac69f62e5
|
Make return_projected_pooled setable from the __init__
|
1 year ago |
|
comfyanonymous
|
ca7c310a0e
|
Support loading old CLIP models saved with CLIPSave.
|
1 year ago |
|
comfyanonymous
|
c2cb8e889b
|
Always return unprojected pooled output for gligen.
|
1 year ago |
|
comfyanonymous
|
1cb3f6a83b
|
Move text projection into the CLIP model code.
Fix issue with not loading the SSD1B clip correctly.
|
1 year ago |
|
comfyanonymous
|
6533b172c1
|
Support text encoder text_projection in lora.
|
1 year ago |
|
comfyanonymous
|
1e5f0f66be
|
Support lora keys with lora_prior_unet_ and lora_prior_te_
|
1 year ago |
logtd
|
e1cb93c383
|
Fix model and cond transformer options merge
|
1 year ago |
|
comfyanonymous
|
10847dfafe
|
Cleanup uni_pc inpainting.
This causes some small changes to the uni pc inpainting behavior but it
seems to improve results slightly.
|
1 year ago |
|
comfyanonymous
|
18c151b3e3
|
Add some latent2rgb matrices for previews.
|
1 year ago |
|
comfyanonymous
|
0d0fbabd1d
|
Pass pooled CLIP to stage b.
|
1 year ago |
|
comfyanonymous
|
c6b7a157ed
|
Align simple scheduling closer to official stable cascade scheduler.
|
1 year ago |
|
comfyanonymous
|
88f300401c
|
Enable fp16 by default on mps.
|
1 year ago |
|
comfyanonymous
|
e93cdd0ad0
|
Remove print.
|
1 year ago |
|
comfyanonymous
|
3711b31dff
|
Support Stable Cascade in checkpoint format.
|
1 year ago |
|
comfyanonymous
|
d91f45ef28
|
Some cleanups to how the text encoders are loaded.
|
1 year ago |
|
comfyanonymous
|
a7b5eaa7e3
|
Forgot to commit this.
|
1 year ago |
|
comfyanonymous
|
3b2e579926
|
Support loading the Stable Cascade effnet and previewer as a VAE.
The effnet can be used to encode images for img2img with Stage C.
|
1 year ago |
|
comfyanonymous
|
dccca1daa5
|
Fix gligen lowvram mode.
|
1 year ago |
|
comfyanonymous
|
8b60d33bb7
|
Add ModelSamplingStableCascade to control the shift sampling parameter.
shift is 2.0 by default on Stage C and 1.0 by default on Stage B.
|
1 year ago |
|
comfyanonymous
|
6bcf57ff10
|
Fix attention masks properly for multiple batches.
|
1 year ago |
|
comfyanonymous
|
11e3221f1f
|
fp8 weight support for Stable Cascade.
|
1 year ago |
|
comfyanonymous
|
f8706546f3
|
Fix attention mask batch size in some attention functions.
|
1 year ago |
|
comfyanonymous
|
3b9969c1c5
|
Properly fix attention masks in CLIP with batches.
|
1 year ago |
|
comfyanonymous
|
5b40e7a5ed
|
Implement shift schedule for cascade stage C.
|
1 year ago |
|
comfyanonymous
|
929e266f3e
|
Manual cast for bf16 on older GPUs.
|
1 year ago |
|
comfyanonymous
|
6c875d846b
|
Fix clip attention mask issues on some hardware.
|
1 year ago |
|
comfyanonymous
|
805c36ac9c
|
Make Stable Cascade work on old pytorch 2.0
|
1 year ago |
|
comfyanonymous
|
f2d1d16f4f
|
Support Stable Cascade Stage B lite.
|
1 year ago |
|
comfyanonymous
|
0b3c50480c
|
Make --force-fp32 disable loading models in bf16.
|
1 year ago |
|
comfyanonymous
|
97d03ae04a
|
StableCascade CLIP model support.
|
1 year ago |
|
comfyanonymous
|
667c92814e
|
Stable Cascade Stage B.
|
1 year ago |
|
comfyanonymous
|
f83109f09b
|
Stable Cascade Stage C.
|
1 year ago |
|
comfyanonymous
|
5e06baf112
|
Stable Cascade Stage A.
|
1 year ago |
|
comfyanonymous
|
aeaeca10bd
|
Small refactor of is_device_* functions.
|
1 year ago |
|
comfyanonymous
|
38b7ac6e26
|
Don't init the CLIP model when the checkpoint has no CLIP weights.
|
1 year ago |
|
comfyanonymous
|
7dd352cbd7
|
Merge branch 'feature_expose_discard_penultimate_sigma' of https://github.com/blepping/ComfyUI
|
1 year ago |
Jedrzej Kosinski
|
f44225fd5f
|
Fix infinite while loop being possible in ddim_scheduler
|
1 year ago |
|
comfyanonymous
|
25a4805e51
|
Add a way to set different conditioning for the controlnet.
|
1 year ago |
blepping
|
a352c021ec
|
Allow custom samplers to request discard penultimate sigma
|
1 year ago |
|
comfyanonymous
|
c661a8b118
|
Don't use numpy for calculating sigmas.
|
1 year ago |
|
comfyanonymous
|
236bda2683
|
Make minimum tile size the size of the overlap.
|
1 year ago |
|
comfyanonymous
|
66e28ef45c
|
Don't use is_bf16_supported to check for fp16 support.
|
1 year ago |
|
comfyanonymous
|
24129d78e6
|
Speed up SDXL on 16xx series with fp16 weights and manual cast.
|
1 year ago |