Image to Flux prompt
Flux rewards detail. Upload a picture and get a dense prompt that names the medium, the light, the lens and the textures, plus guidance and step values to start from.
How your Flux prompt is written
Dense and specific
Style, medium, lens and texture tokens are all spelled out, so Flux has less to guess.
Settings to start from
You get a suggested aspect ratio, step count and guidance value in the parameters line.
Negative prompt included
For ComfyUI workflows and front ends that support it, a full negative prompt comes with every result.
Example Flux prompt
A neon lit alley at night, described the way Flux reads it.
cinematic night photograph of a narrow Tokyo alley after rain, glowing pink and cyan neon signs reflected in wet asphalt, lone figure with a clear umbrella, volumetric haze, 35mm lens, f/1.8, high contrast, rich saturated colors, ultra detailed, photorealistic
How to get a Flux prompt from an image
- 01
Upload your image
JPEG, PNG or WebP. It is resized in your browser first.
- 02
We read the image
Subject, style, lighting, lens, palette and visible text are pulled out.
- 03
Copy the Flux prompt
The Flux tab opens first. Copy it and paste it into Flux.
Flux prompt questions
Which Flux models does it work with?
The prompt is plain text, so it works with Flux dev, schnell, pro and newer Flux releases, in ComfyUI, Forge or any online Flux generator.
Does Flux use negative prompts?
Not every Flux setup reads them. If yours does, paste the negative prompt in its own field. If not, the main prompt already works on its own.
Can I get the same prompt for Stable Diffusion?
Yes. Every upload gives you the Flux and Stable Diffusion prompt together with Midjourney, Nano Banana and a universal version, for one credit.