lllyasviel / lllyasviel/ControlNet

How big should a controlnet dataset be for training?

Open
#569 6 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

The training docs use a 50,000 base image dataset zipped.
The example involves something simple as circles, in a real training setting you might want to create a control for more complex things such as noses or eyes.
It would take months if not years if i tried to manually draw noses outlines for 50,000 images to use to train, without mention find 50,000 good photos.

Just how big should the average dataset be for a non-example controlnet training, realistically?

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 with the training docs and the 50,000-image zipped base-dataset example mentioned in the issue. Compare that simple circles example with non-example controls such as noses or eyes, then define realistic dataset-size guidance for ordinary ControlNet training and document the result.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.