aigc-apps / aigc-apps/VideoX-Fun

Can I use the control model without an input image?

Open
#139 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.3k
Forks
188
Avg merge
2d 22h
Merged PRs (30d)
3

Description

I tried to leave the start_image and clipvision_output blank, but still fed it a control video that had been processes. It 'runs' per se, and the resulting video matches the motion of the control video, however, the resulting video didn't match or even come close the to input prompt (e.g., If I have a control video of a person dancing, and I use a prompt such as "a 25 year old man wearing a green jacket dancing", the resulting video has resemblance to a 25 year old man wearing a green jacket... in fact, its some garbled blobs of a form.

Question is - is the model supposed to work as a control net without the need for a start image or is that just not something it can do?

Thanks!!

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

The issue names start_image, clipvision_output, and a processed control video, but no files or tests. First inspect the model's documented inputs and the control-video entry point; done means confirming whether image-free control is supported and recording the expected behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
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.