Reprompt
Reprompt.org · Coding · Productivity
Reprompt turns any image into a paste-ready text or JSON prompt, and rewrites rough ideas for Midjourney, Flux, and ChatGPT. It's free, needs no account, and ships as a web tool plus an Android app.
About Reprompt
What Is Reprompt
Reprompt is a free AI prompt generator that runs in the browser. You upload a JPEG, PNG, or WebP and get two things back: a written prompt describing the shot, and a JSON prompt that breaks the same image into named fields such as subject, style, lighting, mood, colors, and camera angle. Both are written for the generators people actually use, including Midjourney, Stable Diffusion, Flux, DALL·E, Nano Banana, and GPT Image.
The problem it addresses is the blank page. Rebuilding a look you found in a screenshot usually means guessing at lens, lighting, and palette, then burning a dozen credits while you guess wrong. Reprompt hands you the description first, so the generator starts from a known target instead of a vague idea.
The catch is that a prompt isn't a copy. Reprompt describes what's in the picture, and a generator will produce something similar rather than the same file back. There's also a daily ceiling per visitor plus a pace limit, which is how the site keeps every tool free and ad supported. If you need volume, that cap will get in your way.
Getting Started
- Open reprompt.org and pick a tool, or go straight to the image to prompt page.
- Drag in a photo, paste from the clipboard, or choose a file from your phone gallery.
- Read the generated text prompt, then switch to the JSON view if you'd rather edit one field at a time.
- Copy the result and paste it into Midjourney, Flux, Stable Diffusion, or another generator.
Product Information
A quick look at Reprompt's pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- AI art beginners
- Designers and photographers
- Social media managers
Tasks
- Extracting a prompt from a screenshot
- Rewriting a weak prompt
- Turning a still into a video prompt
Scenarios
- Matching a brand look across a batch of images
- Clearing a creative block on a deadline
- Making a quick prompt on the phone
Key features
Image to Prompt Extractor
The core tool reads an uploaded photo and writes a paragraph that names the subject, style, lighting, mood, palette, framing, and technical structure of the shot. You get one prompt you can paste as-is, no editing required. It handles the three formats people actually screenshot, JPEG, PNG, and WebP, and shrinks the longest side to 1536 pixels before sending so uploads stay fast.
JSON Prompt With 11 Fields
The image to json prompt view splits the same picture into eleven named fields instead of one block of text. That matters when you want to change a single thing, since you can edit lighting without rewriting the sentence around it. The fields match the Reprompt Android app, and the JSON pastes cleanly into Gemini, Nano Banana, or GPT Image. You can also flatten it back into a plain text prompt for Midjourney or Flux.
Prompt Rewriter
Paste a rough idea and the prompt rewriter returns wording shaped for one specific model. Midjourney flags stay separate from the sentence, Stable Diffusion gets a positive and a negative prompt, and Flux, Nano Banana, and GPT Image get phrasing that suits their own quirks. You also see a short note on what changed before you paste, plus two variations to pick from.
Prompt Optimizer Score
The prompt optimizer scores a ChatGPT, image, or video prompt out of 100 across five criteria worth 20 points each, lists the concrete issues it found, and hands back a fixed version. It's the closest thing here to a second pair of eyes, and it teaches you why a prompt underperforms instead of just replacing it.
Image to Video Prompt
Give this tool a still and it writes a video prompt covering shot type, motion, camera move, lighting, suggested duration, and aspect ratio. Veo 3 also gets an audio cue, since that model reads sound. It doesn't generate video. It writes the paragraph you paste into Veo 3, Sora 2, Kling, or Runway, which is the part most people get wrong.
Art Style Identifier
Upload a picture and this tool names the art style, then adds descriptive words you can reuse. It's an estimate rather than a verdict, and that's fine for the job: you get vocabulary like medium, era, and rendering quality that would take a while to pull out of thin air.
Pros and cons
Pros
- Free with no signup: every tool runs without an account, a credit card, or a trial timer.
- Two output shapes: a flat text prompt for quick pasting and an 11-field JSON prompt for surgical edits.
- Model-specific help: the rewriter and video tools account for how Midjourney, Flux, Veo, and Sora differ rather than producing one generic prompt.
- Prompt vocabulary: reading a few extracted prompts is a fast way to learn how style, camera, and lighting words change a result.
Cons
- Daily cap per visitor: a pace limit and a daily ceiling apply, so batch work runs into a wall and you can't plan around it.
- Browser and Android only: there's no iPhone app, so iOS users stay on the website.
- No API: the site publishes no developer interface, which rules out wiring Reprompt into your own pipeline.
Frequently asked questions
Reprompt reads an image and writes the prompt that would describe it, as plain text or as a JSON object with eleven fields. The same site also rewrites rough prompts, scores them, and turns a still into a video prompt.
Related content
Explore related tools, skills, and articles for Reprompt.
Reprompt Alternatives
Base Code
Base44 (Wix) · Coding · ProductivityBase Code is a shared cloud development environment from Base44. Teammates describe changes to an existing GitHub codebase in chat, preview them live and send them back as pull requests.
Google EmbeddingGemma 2
Google DeepMind · Writing · Image · CodingGoogle EmbeddingGemma 2 is a 740M-parameter open model that turns text, code, images, audio, and video frames into vectors in one 768-dimension space, running on phones and laptops.
GitGlow
GitGlow · Coding · ProductivityGitGlow is a local-first desktop Git client that lets independent developers review their own code and their AI agents' changes in one place before shipping.