lllyasviel / lllyasviel/ControlNet

Issue with controling output shape

Open
#687 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
34.1k
Forks
3k
PR merge metrics
No merged PRs in 30d

Description

Hi, thank you for the great work!

When I tried to generate an image conditional on semantic maps, there was an issue with the output shape. According to the definition of the following source code, controlling the output shape by setting height and width is achievable. However, it doesn't work out, for example, input height = 520, width = 480, and the output image could be in other shapes.

https://github.com/huggingface/diffusers/blob/c586aadef6bb66d355fa40a2b95a0bea8a6fe79c/src/diffusers/pipelines/controlnet/pipeline_controlnet.py#L908

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by inspecting the linked pipeline_controlnet.py location around line 908 and reproduce semantic-map image generation with height=520 and width=480. Done means the generated image dimensions consistently match the requested height and width.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.