StepFun's lightweight image generation and editing model for fast text-to-image and prompt-guided image edits. Supports single-image edits and returns edited images at the input image size. Prompts are limited to 512 characters; negative prompts have the same limit.
Added May 11, 2026
Approx. Price
$0.003 per image
Model Type
both
Preview Examples
4
Generation controls available for this model.
Images Per Run
Fixed 1
Resolution Options
6
1024x1024 (Square), 768x1360 (Portrait), 896x1184 (Portrait) +3 more
Tunable Settings
6
CFG Scale
Default
1
Prompt guidance strength. StepFun recommends 1.0 for this model.
Number of Images
Default
1
Resolution
Default
1024x1024
Options (6)
1024x1024 (Square), 768x1360 (Portrait), 896x1184 (Portrait), 1360x768 (Landscape) +2 more
Seed
Default
N/A
Random seed for reproducible outputs. Leave empty for random.
Steps
Default
8
Number of generation steps. StepFun recommends 8 for fast results.
Text Mode
Default
No
Optimization for prompts or edits involving visible text.
Human preference benchmarks sourced from Artificial Analysis.
No Artificial Analysis benchmark data is available yet for this model.
Artificial Analysis API
A ceramic espresso cup shaped like a small lunar lander, glossy white glaze, tiny chrome landing legs, product photography on a warm gray studio backdrop, softbox lighting, crisp shadows
Text-to-image - 1024x1024
A clean isometric app icon of a glass greenhouse with bright tomato plants inside, rounded square composition, polished 3D clay render, white background, subtle shadow
Text-to-image - 1024x1024
A cozy independent bookstore at night, rain on the front window, a black cat sleeping beside a stack of art books, warm amber interior lights, cinematic illustration, detailed but calm
Text-to-image - 1024x1024
Change the mug color to matte cobalt blue, keep the wooden desk, notebook, pencil, lighting, camera angle, and composition the same
Image edit - source image color changed
