Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

how to use with Automatic1111 #1

Open
plasticpippo opened this issue Feb 28, 2024 · 6 comments
Open

how to use with Automatic1111 #1

plasticpippo opened this issue Feb 28, 2024 · 6 comments

Comments

@plasticpippo
Copy link

Hi,
i would like to know if it is possibile to use this model with the webui from automatic1111 o similar ones like Forge or ComfyUI

@lutznw
Copy link

lutznw commented Feb 28, 2024

Don't see a reason it shouldn't, give it a go.

@itsagoodbrain
Copy link

SD.Next supports a lot of models, I'd expect it to get support before automatic1111. I've created a feature request to that end vladmandic/automatic#2926

@cian0
Copy link

cian0 commented Feb 29, 2024

I downloaded the file directly from huggingface under the unet folder but when I load in comfyui it throws an error:
line 49, in detect_unet_config model_channels = state_dict['{}input_blocks.0.0.weight'.format(key_prefix)].shape[0]

@cian0
Copy link

cian0 commented Feb 29, 2024

I downloaded the file directly from huggingface under the unet folder but when I load in comfyui it throws an error: line 49, in detect_unet_config model_channels = state_dict['{}input_blocks.0.0.weight'.format(key_prefix)].shape[0]

Ah this is ok now, just used UNetLoader node for ksampler then checkpoint loader simple to get a clip/vae (not sure if that's needed though)

@youngwanLEE
Copy link
Owner

@itsagoodbrain @cian0 @plasticpippo @lutznw
We have added new KOALA-Lightning models, which result in better quality and faster speed within just 10 steps. Since I haven't tried using the automatic1111 demo system yet, I would appreciate it if someone could test it out.

@itsagoodbrain
Copy link

@youngwanLEE I tried running on SD.Next which is an automatic1111 fork with more support. The original model still works but trying to load the lightning model results in the following error. So I suspect too much has changed for it to be supported automatically. Might reach out to the author here vladmandic/automatic#2926 and see if they wouldn't mind supporting your lightning model as well. They were fast last time at adding it.

10:24:59-845415 ERROR    StableDiffusionPipeline: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory models/Diffusers/models--etri-vilab--koala-lightning-1b/snapshots/cdf96ed0cb72ac4efb3cbe3f5c9a13c269b044bf/text_encoder.
10:24:59-846329 ERROR    Failed loading model: models/Diffusers/models--etri-vilab--koala-lightning-1b/snapshots/cdf96ed0cb72ac4efb3cbe3f5c9a13c269b044bf auto=Error no file named pytorch_model.bin, model.safetensors, tf_model.h5 model.ckpt.index or flax_model.msgpack found in directory models/Diffusers/models--etri-vilab--koala-lightning-1b/snapshots/cdf96ed0cb72ac4efb3cbe3f5c9a13c269b044bf/text_encoder_2. diffusion=Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory                                                  models/Diffusers/models--etri-vilab--koala-lightning-1b/snapshots/cdf96ed0cb72ac4efb3cbe3f5c9a13c269b044bf/text_encoder_2.
10:24:59-847939 WARNING  Model not loaded      

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants