🤯 I didn’t expect Depth to track rooftop parkour this cleanly!
Used a fast climbing clip as the motion reference, then swapped in a student with twin tails and a backpack on a coastal school rooftop.
The running path, wall contact, jumps, landings, and full-body continuity all hold together surprisingly well.
🌟 Workflow:
1. Pick a reference clip under 15 seconds
2. Convert it to Depth with Depth Anything V2
3. Generate a new character + scene
4. Feed everything into Seedance with the prompt below
🌟 Depth video conversion:
You can build a local Depth converter with Codex — prompt in the comments.
Depth opens up a lot more possibilities for parkour, climbing, martial arts, dance, and other complex full-body motion.
Workflow + Prompt below 👇
True. When I came back from the US and joined Kimi, I told my colleagues that many researchers at OpenAI and other frontier labs have access to thousands of GPUs. They were genuinely shocked. It’s incredibly hard to push frontier innovation in China when compute is so scarce.
So we are so proud that our team still made it happen.