Providers and ModelsStepFun

Step Image Edit 2

Step Image Edit 2
StepFun · Image Generation
POST /v1/images/generations

StepFun image generation and image editing model for text-to-image and single-image edits.

At a glance

FieldValue
Model idstep-image-edit-2
Model release date2026-04-29
Input modalitiesText, Image
Output modalitiesImage
Context window-
Weight precision-
RegionInternational
Featuresimage_generation, image_editing, text_rendering
Native inferenceNo
NewYes
Supported endpointsPOST /v1/images/generations, POST /v1/images/edits

Pricing

ChargeSpecRate
Output imageper generated image$0.003

Example request

$curl https://api.empiriolabs.ai/v1/images/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "step-image-edit-2", "prompt": "a misty forest at dawn", "size": "1024x1024"}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringyes-Prompt or edit instruction. Maximum 512 characters. · Max: 512
imageimageno-Reference image URL, data URI, or uploaded image. When present, image editing mode is used.
imagesarrayno-Alias for image. StepFun Image Edit 2 currently uses one input image.
sizeenumno"1024x1024"Output size. · Allowed: 1024x1024, 768x1360, 896x1184, 1360x768, 1184x896
nintegerno1Accepted for API compatibility. StepFun currently returns one image. · Range: 1 – 1
response_formatenumno"url"Return signed image URLs by default or include base64 image data. · Allowed: url, b64_json
seedintegerno-Random seed for reproducible generation. · Range: 0 – 2147483647
stepsintegerno8Sampling steps. · Range: 1 – 50
cfg_scalenumberno1.0Classifier-free guidance scale. · Range: 1 – 10
negative_promptstringno-Negative prompt. Maximum 512 characters. · Max: 512
text_modebooleannofalseEnable text-focused rendering mode.

Notes

Supports text-to-image and single-image editing. Prompt and negative_prompt are limited to 512 characters. Supported sizes are 1024x1024, 768x1360, 896x1184, 1360x768, and 1184x896. n is currently limited to 1.

Content safety

Generated images pass an automated content-safety check. An image flagged as explicit is not returned. Because the image is generated before the check runs, a flagged generation is still billed.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/step-image-edit-2.