lllyasviel / lllyasviel/ControlNet

Plans for an openpose model including hand pose data?

Open
#53 10 comments 5 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

Are you guys planning on eventually training an openpose model, including handpose data?
https://github.com/Hzzone/pytorch-openpose#hand-pose-estimation

I feel like if we had the openpose model usable with hand data then stable diffusion will finally be able to consistently reproduce hands/fingers.
I'm assuming the biggest hurdle will be obtaining enough annotated data to produce such a model in the first place though.

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

No files, tests, or entry points are named. The issue asks about a future hand-pose model and its annotated-data requirements, so a contributor would first need a maintainer to define the desired scope, training approach, and acceptance criteria.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
18/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.