Dracula Hand Dance
Editor's note
A deadpan Dracula runs a hand-and-finger routine on the beat in front of a hushed crowd. Both hands stay in frame, so the fingers have to hold up.
@Video1 controls motion, camera, framing, timing, and sound; keep all of it exactly: the static waist-up shot and the whole hand and finger routine on the beat - crossed fists at the chest, a triangle made with the fingertips, palms crossed flat on the chest, fingers interlaced into a pyramid, fingers flicking and parting, then palms rolling over each other in front of the chest. Both hands stay in frame the whole time, five fingers on each hand, short nails, no claws. @Image1 controls the identity of the performer: replace him in every frame with the person from @Image1, including face, hair, build, outfit, and any special features such as eye colour or fangs, which stay visible in every frame. Calm deadpan face looking straight into the lens, no smile. No trace of the original. If @Image2 is provided, it controls the location: replace the environment and the crowd behind him to fit that place, with everyone dressed to match it. If @Image2 is not provided, keep the original environment. From @Video1 take only the motion and the camera; take none of its people, clothes, props or walls. One continuous shot, no cuts, no subtitles, no text.
What You Need
The prompt points to each file by its tag, like @Video1. Download the examples or bring your own.
How to Use This Prompt
- 1Copy the prompt above — the full text, not a trimmed version.
- 2Open Workroom: Video → WAN 3.0. Use reference mode; in settings pick 720p or 1080p and 6 seconds.
- 3Upload the files in this order: Video 1 → Image 1 → Image 2.
- 4Paste the prompt and hit Generate. Check the first result before making more.
Every prompt in the library works the same way — copy, paste into the model, generate.
Explore More Video PromptsSame Workflow, Other Results
Same prompt and Video 1, different Image 1 and Image 2.
All Video Models
Every prompt here was actually run.
Workroom is one account for every image and video model — pick any prompt above, or start from scratch.

