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

It is not work when using the base model in safetensors format. #17

Open
l-dawei opened this issue Dec 25, 2023 · 5 comments
Open

It is not work when using the base model in safetensors format. #17

l-dawei opened this issue Dec 25, 2023 · 5 comments

Comments

@l-dawei
Copy link

l-dawei commented Dec 25, 2023

When I use the basic model in safetensors format, the error is as follows:

T60E5dvnjQ

Who can help me?

@horseee
Copy link
Owner

horseee commented Dec 25, 2023

Hi @l-dawei,

Could you check which UNet2DConditionModel the code would call? The one in diffusers or the one in DeepCache/sdxl/unet_2d_condition.py

@l-dawei
Copy link
Author

l-dawei commented Dec 26, 2023

Hi @l-dawei,

Could you check which UNet2DConditionModel the code would call? The one in diffusers or the one in DeepCache/sdxl/unet_2d_condition.py

I checked and found that if I use the from_single_file function to load, the UNet2DConditionModel of diffusers is still called.

@l-dawei
Copy link
Author

l-dawei commented Dec 27, 2023

Hi @l-dawei,

Could you check which UNet2DConditionModel the code would call? The one in diffusers or the one in DeepCache/sdxl/unet_2d_condition.py

When I use from_pretrained and from_single_file the different unet_2d_condition is called.

@horseee
Copy link
Owner

horseee commented Dec 27, 2023

Hi @l-dawei,

Could you check if the new implementation works?

@l-dawei
Copy link
Author

l-dawei commented Dec 27, 2023

Hi @l-dawei,

Could you check if the new implementation works?

It's so powerful.

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

2 participants