lllyasviel / lllyasviel/ControlNet

Issues with Training Data

Open
#487 2 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

Is it feasible to use a dataset that consists of images with sizes like 512x832, 512x576, 1536x512, etc. for training?

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 tracing ControlNet's training-data handling and how it processes image dimensions. Evaluate the reported 512x832, 512x576, and 1536x512 cases against the training pipeline, and document whether these dimensions are supported or what constraints apply.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.