Prompt-guided image editing for one to five reference images, with controls for output format and aspect ratio.
Added May 12, 2026
Approx. Price
$0.010 per image
Model Type
image-to-image
Preview Examples
3
Generation controls available for this model.
Images Per Run
Up to 4
Resolution Options
1
auto (Match input image)
Tunable Settings
5
Aspect Ratio
Default
match_input_image
Options (8)
Match input, Square, Landscape 16:9, Portrait 9:16 +4 more
Control the edited image shape.
Number of Images
Default
1
Output Format
Default
png
Options (3)
PNG, JPEG, WebP
Output image format.
Resolution
Default
auto
Options (1)
auto (Match input image)
Seed
Default
-1
Control reproducibility (-1 for random).
Human preference benchmarks sourced from Artificial Analysis.
Image Editing
#29 / 60
ELO
1157.0
Appearances
4,372
95% CI
-9/9
Release Date 2025-11 · Matched as P-Image-Edit
Artificial Analysis API
Add a teddy bear next to the character reading a book, matching textures while preserving the overall style and keeping all other elements unchanged.
Image edit - match input image

Change background, object, and setting while preserving the main subject identity, proportions, and image style.
Image edit - prompt adherence

Take the mountain from image 1. Take the sky from image 2. Take the man on the rocks from image 3.
Multi-image edit