Paper Unfold Frames
Photo-real stop-motion of a crumpled paper ball opening into a note, made from GPT-image keyframes.
CreativeSkillPackaged
Installation
Version 1.0.1 · One skill: SKILL.md, a frame keying script, two working prompts, a playback snippet and the licence. No media.
Download the focused package
Download the ZIP from the release and extract it. It holds only the skill folder; preview media and translations stay on separate branches of the repository.
Release v1.0.1 ↗Add it to your agent
Copy the extracted folder into your agent's skills directory (Claude Code: ~/.claude/skills/), or install it straight from main with git.
git clone --depth 1 https://github.com/OpenRootdev/paper-unfold-frames ~/.claude/skills/paper-unfold-framesAsk for an unfold
Describe the shot in plain words, for example: "Open the video with a crumpled note that unfolds to show our tagline." The agent generates a 3x3 grid of stages, keys out the frames and plays them stepped at 6-8 fps.
Manual setup
- Access to a GPT image model, for example through the Figma MCP generate_image tool or the OpenAI API.
- Python 3 with Pillow, numpy and scipy to key out the frames.
- A canvas-based video tool such as HyperFrames or Remotion, or a web page.
Additional notes
- Handwriting or a sketch can be baked into the image prompt so it is revealed as the sheet opens.
- Sister skill: Paper Unfold Mesh draws the same effect procedurally in code.