Skip to content

During inpainting, scaling latent before concat break some schedulers. #1276

Closed
@BurguerJohn

Description

@BurguerJohn

Describe the bug

In pipeline_stable_diffusion_inpaint.py there is this two lines:

latent_model_input = torch.cat([latent_model_input, mask, masked_image_latents], dim=1)
latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

It seen to break some schedulers, setting scale first should fix it:

latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
latent_model_input = torch.cat([latent_model_input, mask, masked_image_latents], dim=1)

Reproduction

No response

Logs

No response

System Info

Windows

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions