P-Image prompt-guided editing with optional external LoRA weights and one to five reference images.
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
8
Aspect Ratio
Default
match_input_image
Options (8)
Match input, Square, Landscape 16:9, Portrait 9:16 +4 more
Control the edited image shape.
LoRA Scale
Default
1
Scale for the LoRA weights.
LoRA Weights
Default
N/A
External LoRA weights URL.
Number of Images
Default
1
Output Format
Default
png
Private Weights Token
Default
N/A
Optional token for private or gated LoRA weights.
Resolution
Default
auto
Options (1)
Human preference benchmarks sourced from Artificial Analysis.
No Artificial Analysis benchmark data is available yet for this model.
Artificial Analysis API
sks_comic_noir, change the background to a rainy noir street and add a glowing shop sign, preserve the subject pose and composition, apply bold black-and-white ink shadows.
Image edit LoRA - match input image
sks_comic_noir, update the visible poster text and keep the person, layout, and camera angle unchanged, with high-contrast inked shadows and vintage pulp styling.
Image edit LoRA - text edit
sks_comic_noir, combine the mountain from image 1, the sky from image 2, and the person from image 3 into one cohesive noir comic scene.
Multi-image edit LoRA
auto (Match input image)
Seed
Default
-1
Control reproducibility (-1 for random).
