IMAGE → PROMPT

Turn a reference image into a better prompt.

Upload a reference, add examples, and keep refining one precise prompt with the Assistant.

CHOOSE A WORKFLOW

What do you want to make?

Image → PromptDescribe a reference in detail Prompt → PromptPolish an idea into a ready prompt Edit an ImageChange a reference with instructions

MODEL SETTINGS

Choose the model for each workflow

Selections are saved for your next visit. Costs are estimates shown by the platform.

Image → Prompt

Vision models that can inspect reference images.

Prompt → Prompt

Text models for rewriting and refining prompts.

Edit an Image

Only Flux Kontext editors. Safety is set to 6 (least strict).

Model discovery is unavailable, so the built-in compatible defaults are being used.

01 / REFERENCE

Add a reference image

Choose an imageor drop it hereJPG, PNG, WebP or GIF · up to 5 MB

No image selected

Your image preview will appear here

Remove image

01 / REFERENCE

Start with a prompt

Your starting prompt

The Assistant will keep your intent, improve the visual structure, and return a prompt, tags, negative prompt, and image specs.

02 / DIRECTION

Set the level of visual detail

Detail intensity80%

Higher values ask for precise visual detail without inventing facts.

Optional direction for the first pass

The Assistant returns the prompt, tags, negative prompt, and image specs together.

What should change?

Original similarity80%

Higher values make only the requested edits.

Creativity35%

Higher values explore the instruction while keeping characters and art style unless asked otherwise.

Upload a reference, describe the change, then balance preservation and invention.

Vision model for this run

This vision model inspects your reference for the next prompt.

Generate detailed prompt↗

03 / RESULTS

Your prompt is ready

Copy all

Detailed prompt

Tags & weights

Negative prompt

Image specs

Generator and resolution are estimates unless embedded metadata is available.

04 / REFINE

Talk to the Assistant

Ask for an edit, addition, or correction. The current image and prompt stay in context.

Message the Assistant

Add examplesUpdate prompt

03 / RESULTS

Your edited image is ready

Open image

Your edited image will appear here.

EDIT APPLIED