P-Image text-to-image generation with optional external LoRA weights.
Added May 12, 2026
Approx. Price
Varies per image
Model Type
text-to-image
Preview Examples
3
Generation controls available for this model.
Images Per Run
Up to 4
Resolution Options
7
1024x1024 (Square (1:1)), 1376x768 (Wide Landscape (~16:9)), 1184x896 (Landscape (~4:3)) +4 more
Tunable Settings
7
LoRA Scale
Default
0.5
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
1024x1024
Options (7)
1024x1024 (Square (1:1)), 1376x768 (Wide Landscape (~16:9)), 1184x896 (Landscape (~4:3)), 1248x832 (Landscape (~3:2)) +3 more
Seed
Human preference benchmarks sourced from Artificial Analysis.
No Artificial Analysis benchmark data is available yet for this model.
Artificial Analysis API
sks_comic_noir, a mysterious detective standing under a broken streetlamp in a rain-soaked alley, dramatic silhouette, high contrast black and white with bold shadows, vintage pulp comic cover style, heavy ink lines
Text-to-image LoRA - 1024x1024

sks_comic_noir, a retro science-fiction poster of a lone pilot beside a chrome rocket, moonlit clouds, bold halftone shading, hard rim light, vintage pulp illustration
Text-to-image LoRA - 1024x1024

sks_comic_noir, close-up character portrait of a confident private investigator, trench coat collar raised, rain streaks on glass, sharp inked shadows, cinematic noir lighting
Text-to-image LoRA - 1024x1024
Default
-1
Control reproducibility (-1 for random).