Skip to content

Quatered image produced, StableDiffusionPanoramaPipeline #3769

@inkyusa

Description

@inkyusa

Describe the bug

Hi,
Anyone experienced the following when running the multidifussion tutorial?
It generates a quater dolomites with the default setup but, correct one with height=1024

Reproduction

Just did as shown in https://huggingface.co/docs/diffusers/main/en/api/pipelines/panorama

import torch
from diffusers import StableDiffusionPanoramaPipeline, DDIMScheduler

model_ckpt = "stabilityai/stable-diffusion-2-base"
scheduler = DDIMScheduler.from_pretrained(model_ckpt, subfolder="scheduler")
pipe = StableDiffusionPanoramaPipeline.from_pretrained(model_ckpt, scheduler=scheduler, torch_dtype=torch.float16)

pipe = pipe.to("cuda")

prompt = "a photo of the dolomites"
image = pipe(prompt).images[0]  #1/4
#image = pipe(prompt, height=1024).images[0] #looks ok.
image.save("dolomites.png")

quater-dolomites

Logs

No response

System Info

  • diffusers version: 0.18.0.dev0
  • Platform: Linux-5.15.0-69-generic-x86_64-with-glibc2.27
  • Python version: 3.9.16
  • PyTorch version (GPU?): 1.13.0 (True)
  • Huggingface_hub version: 0.15.1
  • Transformers version: 4.29.2
  • Accelerate version: 0.18.0
  • xFormers version: not installed
  • Using GPU in script?: yes
  • Using distributed or parallel set-up in script?: no

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