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

Trouble with Setting Custom Image Resolution #9

Open
SlZeroth opened this issue Aug 8, 2023 · 1 comment
Open

Trouble with Setting Custom Image Resolution #9

SlZeroth opened this issue Aug 8, 2023 · 1 comment

Comments

@SlZeroth
Copy link

SlZeroth commented Aug 8, 2023

I don't want a 512x512 resolution result, but want to set the resolution. In the source code below, I set the width to 512 and the height to 768. However, the result is a 512x512 resolution image.

Am I making a mistake or is there something I should refer to?

@torch.no_grad()
def text2image(
    model,
    prompt:  List[str],
    controller,
    num_inference_steps: int = 50,
    guidance_scale: Optional[float] = 7.5,
    generator: Optional[torch.Generator] = None,
    latent: Optional[torch.FloatTensor] = None,
    uncond_embeddings=None,
    start_time=50,
    return_type='image'
):
    batch_size = len(prompt)
    register_attention_control(model, controller)
    height = width = 512
@g-jing
Copy link
Collaborator

g-jing commented Nov 23, 2023

Sorry but we do not support that in this project as it is limited by the stable diffusion backbone. Our ongoing work will be able to support that, and that will be released soon. Please stay tuned!

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