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 condition on an image? #74

Open
amirshamaei opened this issue Mar 15, 2024 · 2 comments
Open

How to condition on an image? #74

amirshamaei opened this issue Mar 15, 2024 · 2 comments

Comments

@amirshamaei
Copy link

I was wondering if it is possible to condition the input on an image? since the scale size is (Bdim) so how we can scale the input (BLdim) using an image. Should I patch the image to size of (B, pp , dim)?

@tanghengjian
Copy link

you mean text condition ? if so, i will try to make it , but the data preparation of text-image pairs may spent a lot .

@emergencyd
Copy link

I guess you can refer to latent diffusion inpainting. Just concat your encoded input image, resized condition mask, encoded masked image to a multi-channel input.

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

3 participants