AI Image Editor
One sentence, the change you want.
Upload one main image and up to 9 reference images, then describe the change. You can also box a region on the main image to edit only that area. AI adapts the input size and returns an image close to the original aspect ratio.
Drop images here (multiple allowed)
JPG / PNG / WebP · up to 10 MB each · max 10 images
Same image, changed as described.
Upload an image and describe the change; AI edits the scene accordingly. Drag the slider to compare.
Edit an image with one sentence.
Main image plus references, local selections, automatic sizing and usage-based pricing.
Main + up to 9 references
Use references for style, people, products or backgrounds.
Only the boxed area
Box a region on the main image; everything outside stays the same.
Keep the subject, restyle everything.
Keep the subject and structure while restyling the whole image.
Make the subject face the camera.
Turn the subject toward the camera with a toothy smile.
More than four ways to edit.
The four below are just examples; backgrounds, styles, elements and people can all be edited the same way.
Add creative elements
Place something that was never there, like a giant cat in a street scene. The subject, perspective and lighting stay consistent, so the new element blends into the scene. Great for posters, social visuals and playful composites.
Turn photos into illustration
Keep the pose, expression and composition, and restyle the whole photo as a comic, illustration or hand-drawn artwork. Background, line work and color are reworked together, more than a filter, for avatars, covers, storyboards and brand visuals.
Remove unwanted elements
Delete people or objects from a group photo or scene, and rebuild the wall, table and floor they were covering. Lighting and textures stay continuous, so the retouch is hard to spot, handy for team photos and event shots.
Stage product shots
Keep the product and its logo, then drop a white-background shot into a lifestyle scene with plants, frames and natural light. Background, lighting and shadows are adjusted together for a more editorial product image.
Upload, box, describe, edit.

Upload main & references
The first image is the main one; the rest are references, up to 10 total.

Box & describe
Optionally box a region on the main image, then describe the change.

Compare & download
Check the result and download it.
Photoshop AI / Canva AI vs. Eyesme image editor.
AI Image Editor vs Photoshop AI
| Photoshop AI | AI Image Editor | |
|---|---|---|
| Getting started | Requires layers, masks, curves and Generative Fill | Upload in the browser, write a short description and add up to 9 references |
| Core capability | Manual selections and local repainting; depends on skill | A main image plus references, edited by description |
| Consistency | Manual work is hard to keep consistent | Descriptions and references keep similar edits consistent |
| Environment | Desktop install, depends on hardware | Runs in the browser, no install |
| Best for | Professional retouchers and design teams | Portrait retouching, product scenes, content visuals and creative composites |
AI Image Editor vs Canva AI
| Canva AI | AI Image Editor | |
|---|---|---|
| Core capability | Template- and Magic Edit-driven; complex work is limited | A main image plus references, edited by description |
| Steps | Choose a template, edit, export | Upload, describe or box a region, download |
| Consistency | Depends on templates and assets; style is hard to unify | Descriptions and references keep results predictable |
| Original preserved | Depends on the template and edit scope | Keeps the main image's composition, subject and proportions |
| Best for | Social posters, template design and light edits | Portrait retouching, product scenes, content visuals and creative composites |
About AI image editing
How does AI Image Editor work?
Upload the main image first, optionally add up to 9 reference images, box a region to change (optional), then describe the edit. AI generates a new image based on the main image.
What are reference images for?
Use references to specify style, people, products or backgrounds. The first image is always the main image being edited; references are guidance only and are not pasted into the result.
Can I edit only part of the image?
Yes. Box a region on the main image and AI changes only that area, leaving the rest untouched. Without a box, the whole image is editable.
How is the output size decided?
The server computes a size as close as possible to the main image aspect ratio while satisfying the model: both sides divisible by 16, aspect ratio between 1:3 and 3:1, longest side at most 2560. The main image is center-cropped to the target aspect ratio, then resized.
Which formats are supported?
JPG, PNG and WebP, up to 10 MB per image; up to 10 images including the main image and references.
Do I get charged if it fails?
No. Credits are deducted only after the result is generated and saved. Upload failures and upstream errors are free.
How do I change the background or style?
Upload the main image and describe the new scene or style, stating what to keep: the subject, composition and lighting. Add up to 9 references if you need visual guidance.
How do I write a better edit description?
Say what to change and what the result should look like, then list what must stay the same; for example, “replace the taxi on the right with a red sports car, keeping the other cars, road and lighting unchanged.” More specific descriptions give more predictable results.
Explore more tools
Design & visual
AI Style Poster
One photo, eighteen poster styles
AI ID Photo Generator
Resume · Job application · LinkedIn, from one selfie
AI Skin Beautify
Four levels, from natural to flawless
AI Cinematic Lighting
12 cinematic color grades, one click away
AI Background Remover
Remove the background and export a transparent PNG
AI Film Colorizer
12 classic film color palettes for black-and-white photos
AI Slow Shutter
Silky long-exposure water and flowing city motion
AI Portrait Background Blur
Classic lens depth of field, sharp subject and soft background
