A 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
Settings
Generation controls available for this model.
Images Per Run
Fixed 1
Output images
Input Images
Up to 1
Reference/edit images accepted • Provider max 30 MB
Output Sizes
CFG Scale
Default
1
Prompt guidance strength. Recommended value: 1.0.
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. Recommended value: 8 for fast results.
Text Mode
Default
No
Optimization for prompts or edits involving visible text.
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#134 / 159
ELO
810.0
Appearances
2,592
95% CI
-10/10
Image Editing
#34 / 76
ELO
1005.0
Appearances
4,304
95% CI
-9/9
Release Date 2026-05 · Matched as Step Image Edit 2
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare Step Image Edit 2 with similar models from the same provider or model family.
GPT Image 2.5 Flare Edit
openai/gpt-image-2.5/flare/editGPT Image 2.5 Flare edits images from natural-language instructions with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.
GPT Image 2.5 Sunburst Edit
openai/gpt-image-2.5/sunburst/editGPT Image 2.5 Sunburst edits images from natural-language instructions with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.
MiniMax H3 Image Edit
wavespeed-ai/minimax-h3/image-editEdit images from up to nine references, preserving identity while changing scenes, outfits, or styles. Supports 1K and 2K output.
Grok Imagine Image 2.0 Edit
xai/grok-imagine-image/v2.0/editGrok Imagine Image 2.0 Edit applies prompt-guided changes using up to three input images, with flexible aspect ratios, 1K or 2K output, and selectable low or medium quality. Requests rejected under SpaceXAI's terms may still incur a provider charge.
Reve 2.1 Edit
reve/2.1/editReve 2.1 Edit applies precise natural-language changes to one reference image with native 4K output and accurate text rendering.
Boogu Image Edit
fal-ai/boogu-image/editBoogu Image Edit transforms one uploaded image from natural language instructions.