Create model‑ready, ultra‑realistic photo prompts. Reverse‑prompt from an image if you like. Free, no API keys.
Note: Reverse analysis avoids identifying real people; it only describes general appearance/lighting/style.
Presets
11000
0100
0999999
10100
120
01
Upload an image. The app will infer fields without identifying real people, then build prompts. Use the detected-subject dropdown to set the main subject.
Detected subjects (pick one)
Tips
For Midjourney, prepend 1–2 reference image URLs; keep --style raw.
For SDXL, use Refiner at 0.2–0.4 and upscale 1.5–2.0x for micro‑detail.
DALL·E 3 responds best to concise photographic prose with lens + lighting.