Image Editing
Edit an Existing Photo With Clear Instructions AI Photo Prompt
Describe a precise photo edit so a model changes only what you asked and leaves the rest alone.
The Prompt
edit-an-existing-photo-with-instructions.md
You are a retoucher writing edit instructions for an image model. Current photo (describe it): {{current_photo}} Change I want: {{change}} Must stay identical: {{keep}} Output use: {{use}} Write: 1. A single instruction block: what to change, what to preserve (face identity, pose, crop, lighting direction, logos). 2. A "do not" list of five common over-edits for this request. 3. A short inpainting prompt if only a region should change. 4. Suggested output size / aspect - match the original unless a crop is requested. If the requested change would break realism (wrong lighting, extra fingers, warped text), say so and propose a safer version.
Negative prompt
Included when you copy the prompt
Do not change face identity, pose, crop, or lighting direction unless asked. Do not over-smooth skin, invent logos, warp text, add extra fingers, or recolor unrelated regions. Prefer a safer edit if the request would break realism.
Fill in your details below - this prompt updates as you type, then copy it.
Fill in your details
0 of 4 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).
edit-an-existing-photo-with-instructions.md
Prompt preview
You are a retoucher writing edit instructions for an image model. Current photo (describe it): {{current_photo}} Change I want: {{change}} Must stay identical: {{keep}} Output use: {{use}} Write: 1. A single instruction block: what to change, what to preserve (face identity, pose, crop, lighting direction, logos). 2. A "do not" list of five common over-edits for this request. 3. A short inpainting prompt if only a region should change. 4. Suggested output size / aspect - match the original unless a crop is requested. If the requested change would break realism (wrong lighting, extra fingers, warped text), say so and propose a safer version.
Examples
Example input
Current photo: outdoor product shot of a navy backpack on a wooden bench, slight underexposure, busy leaves in the background. Change: brighten exposure, blur background, keep bag colour true. Keep: logo patch, strap layout, crop. Use: Amazon listing hero.
What you should get
One instruction block preserving identity of bag/logo/crop; a five-item do-not list (no recolor, no logo invent, no warp); a short inpainting prompt for background only; output size matching original - flags any realism risk and offers a safer alternative.
How to use this AI photo prompt
- Upload a clear reference photo of your face (well-lit, front-facing works best).
- Fill any placeholders on this page, then tap Copy Prompt.
- Paste into ChatGPT (also works with Gemini, Flux) and generate.
- Keep your face locked - only wardrobe, pose, and scene should change.
Privacy: If you attach a face reference, do it in the AI tool. Codextroop Prompt Library never receives or stores your photos.
Works best with ChatGPT / Gemini / Flux
Identity-preserving image-to-image prompts need a strong face reference. Avoid heavy beauty filters on the upload and use the negative prompt when your tool supports it.
Tips for better image editing results
- Match the example aspect ratio when your tool allows it (often 4:5 for portraits).
- If the face drifts, re-upload a sharper photo and keep the same prompt text.
- Copy related image editing prompts below to try alternate looks with the same identity lock.
When to use this prompt
Use it when
- You need help with designers.
- You need help with sellers.
- You need help with social teams.
Skip it when
- You only need a one-line ask with no constraints, format, or context.
- You cannot supply the fill-in details the template asks for.
- You want a modern digital look or heavy filter effect instead of the era/style this prompt targets.
How to get a good result
Done when
One instruction block preserving identity of bag/logo/crop; a five-item do-not list (no recolor, no logo invent, no warp); a short inpainting prompt for background only; output size matching original - flags any realism risk and offers a safer alternative.
Common mistakes
- Leaving current_photo, change, keep vague - the model then invents placeholders.
- Asking ChatGPT, Gemini, or Flux for a shorter answer after a long structured prompt - that throws away the format rules.
- Stopping when the first draft appears instead of checking it against the success criteria below.
FAQ
- What do I fill in before I copy this prompt?
- Replace these placeholders with your details: current_photo, change, keep, use. Required fields are marked on the page. The prompt text updates as you type.
- Which AI tools is this prompt written for?
- It works best with ChatGPT, Gemini, Flux. Copy the filled prompt and paste it into the tool you already use.
- What should a good result look like?
- One instruction block preserving identity of bag/logo/crop; a five-item do-not list (no recolor, no logo invent, no warp); a short inpainting prompt for background only; output size matching original - flags any realism risk and offers a safer alternative.
- What are common mistakes with this prompt?
- Leaving current_photo, change, keep vague - the model then invents placeholders. Asking ChatGPT, Gemini, or Flux for a shorter answer after a long structured prompt - that throws away the format rules. Stopping when the first draft appears instead of checking it against the success criteria below.
Best for
- Designers
- Sellers
- Social teams
Related Prompts
More prompts like this — same topic and style.