Image to prompt
Image to prompt: a free tool that runs entirely in your browser. No sign-up, nothing uploaded.
Drop a reference image: palette, brightness, contrast, orientation and composition are read in the browser and written into a prompt skeleton for image-to-video.
FAQ
What does the tool read from the image?
Dominant colours (a 4-bit histogram of sampled pixels), mean brightness, contrast (luma spread), saturation, warm/cool balance, orientation and aspect ratio, and where the visual energy sits on a rule-of-thirds grid. It does not recognise objects; you write the subject.
Is the image uploaded?
No. It is decoded by your browser, drawn to a canvas, and the pixels are analysed there. Nothing is sent anywhere.
What is the prompt for?
Image-to-video: upload the same image as the first frame in Veo, Kling, Runway or Luma and paste this prompt, so the motion request keeps the look the frame already has. It also works as a style lock for text-to-video.
From the library
Image-to-video: generate the first frame, then animate it
Make a still with an image model first, fix the composition there, and only then ask the video model to animate it. Cheaper iterations and the look you chose, not the one the video model guessed.
Style lock: one paragraph that makes every clip look like the same film
A reusable style paragraph (stock, palette, grain, light rules) appended to every generation prompt so a series cuts together instead of looking like ten different ads.
Keep the same character across clips: the reference sheet prompt
A character description block you reuse verbatim in every prompt, plus a generated reference sheet, so a face, outfit and build stay the same from shot to shot.
Related tools: Veo 3 prompt generator · Frame grabber
All tools: Veo 3 prompt generator · Video prompt builder · Script, shot list and prompt list · Frame grabber · Safe-zone and aspect-ratio overlay · Caption reading-speed checker · Hook generator