aigc-apps / aigc-apps/VideoX-Fun

Shape Error in Wan2.2-Fun-5B-Control-Camera

Open
#293 1 comment 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

Thanks for sharing Wan2.2-Fun-5B-Control-Camera!

When I run the model for inference, I met the following error:
RuntimeError: Given groups=1, weight of size [3072, 100, 1, 2, 2], expected input[1, 48, 21, 30, 52] to have 100 channels, but got 48 channels instead

I found that the shape of patch_embedding.weight is [3072, 100, 1, 2, 2], but the output channel of previous layers is 48. This really confuses me.

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

Begin by reproducing the Wan2.2-Fun-5B-Control-Camera inference failure and tracing the input shape into patch_embedding. Compare the reported 48-channel preceding output with the layer's expected 100 channels; done means inference proceeds without this shape mismatch.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.