Analyze a Reference Image and Create an Original Image Prompt

Use GPT to break down a reference image’s visual qualities, then apply them to a new concept without copying the original image.

ubermingcourse Republished on Oct 23 0 Bookmarks 0 Copies
Bookmark 0

Example outputs

Example result for Analyze a Reference Image and Create an Original Image Prompt

Prompt template

Format
Text Parameterized
Inputs
Reference_image (image) · Required Creative_direction (text) · Required
Outputs
Image_generation_prompt (text)
Analyze the uploaded reference image’s composition, camera, lighting, colors, materials, and visual style. Summarize the visual qualities that make it effective.

Then create an image-generation prompt based on those visual qualities, adapted to this new creative direction: ${creative-direction}

Preserve the reference’s visual language, but replace its original characters, setting, subject, and story with the new concept. Do not directly copy the reference image. Make the final prompt clear and ready to use for AI image generation.

Replace the ${…} placeholders with your values before using this prompt. See parameters and defaults below

Parameters

Replace each placeholder with your own value, or use its default when one is provided

${creative-direction} creative-direction Required

What you'll create

A short visual analysis identifies composition, camera, light, color and materials, then informs a new image prompt for a different creative direction.

Frequently asked questions

Should the original story be copied?

No, characters, setting, subject and narrative are replaced while the visual language is retained.

Comments

Tried this prompt? Share what you made, compare results, or ask a question

Up to 4 results. Images up to 2 MB; MP4, WebM, or MOV videos up to 4 MB each