Reprise un-flattens a finished, flat AI design (ChatGPT/Midjourney/Claude) back into editable layers and rebuilds it bit-perfect — it returns a fidelity score (MAE 0.00 / 0 stray px) so you can verify, not just trust. Reproducing runs locally and free; remix one design into N on-brand variants. Tools: reproduce / autodetect / diagnose. Try it (no signup): https://tepesama-reprise-mcp.hf.space/
Overview
What it does
Reprise turns a finished, flat AI design (ChatGPT / Midjourney / Claude) back into editable layers and rebuilds it bit-perfect — and returns a fidelity score (MAE 0.00 / 0 stray px) so you can verify, not just trust. Reproducing runs locally and free; remix one design into N on-brand variants.
Try it (no signup)
Open https://tepesama-reprise-mcp.hf.space/ → the "Try it" tab → drop an image (or click the sample).
Add as MCP
claude mcp add --transport http reprise https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http
Tools
- reproduce(image) → editable layers + fidelity score
- autodetect(image) → detected elements
- diagnose(original, reproduction) → fidelity metrics
Honest by design: unedited layers are bit-perfect; edited regions are newly generated. Auto element-detection is v1.
Product / early access: https://reprise.design
Server Config
{
"mcpServers": {
"reprise": {
"type": "http",
"url": "https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http"
}
}
}