[Video 1 - Picture 1 to Video]:

### Confirmation

- [x] I have confirmed this is a workflow template mistake

### Template Name

video minimax h3 r2v

### Problem Description

How does this work?
I've been trying to figure this out for days. Google AI and GPT aren't helping. Unfortunately, none of their suggestions work.
What's the correct prompt?
Image 1 should replicate the exact movement from Video 1. Just the movement! Nothing else! No changing clothes or anything like that. JUST THE MOVEMENT!
And Image 1 should also speak the audio from Audio 1.

### ComfyUI Mode

Legacy Mode

### Error Message / Logs

```text
no
```

Start by opening the legacy-mode `video minimax h3 r2v` workflow template and reviewing its prompt and audio/video inputs. Determine how the template should make Image 1 follow Video 1's movement while preserving appearance and using Audio 1, then verify the corrected workflow against those requirements.

Written by the indexing model from the issue text.