Image Model Integration - StepFun Documentation

Step Plan supports image generation/editing models via a dedicated path. All requests use the /step_plan/v1/... path prefix, with the domain fixed as https://api.stepfun.ai.

Prerequisites

Subscribed to a Step Plan.
Obtained an API Key.

Image Generation / Editing Models

Supported Models

Model	Description
`step-image-edit-2`	Lightweight image generation/editing model. A single model supports both text-to-image and image editing; each editing task takes only 1-2 seconds, with input images supporting up to 4096x4096 resolution.

Endpoint Paths

Capability	Request Method	Step Plan Path
Text-to-image	POST	`https://api.stepfun.ai/step_plan/v1/images/generations`
Image editing	POST	`https://api.stepfun.ai/step_plan/v1/images/edits`

The endpoint parameters are exactly the same as the open platform. For details, refer to the API documentation: Generate images, Image editing.

Billing Instructions

The billing logic is consistent with the open platform. Ultimately, the actual billed amount calculated on the open platform will be converted into Step Plan total quota consumption. For specific unit prices, please refer to Pricing and Rate Limits.

Examples

Text-to-image (curl)
Image editing (curl)
Python (OpenAI SDK)

curl -X POST 'https://api.stepfun.ai/step_plan/v1/images/generations' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer $STEP_API_KEY" \
-d '{
    "model": "step-image-edit-2",
    "prompt": "A serene alpine lake at sunset, mirror reflection, photorealistic",
    "response_format": "b64_json",
    "cfg_scale": 1.0,
    "steps": 8,
    "seed": 1,
    "text_mode": true
}'

curl -X POST 'https://api.stepfun.ai/step_plan/v1/images/edits' \
-H "Authorization: Bearer $STEP_API_KEY" \
-F 'model=step-image-edit-2' \
-F 'image=@input.webp' \
-F 'prompt=Make the character ride a bicycle, holding a sign that says "Saudi Arabia"' \
-F 'response_format=b64_json' \
-F 'cfg_scale=1.0' \
-F 'steps=8' \
-F 'seed=1' \
-F 'text_mode=true'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_STEP_API_KEY",
    base_url="https://api.stepfun.ai/step_plan/v1",
)

image = client.images.generate(
    model="step-image-edit-2",
    prompt="A serene alpine lake at sunset, mirror reflection, photorealistic",
    response_format="b64_json",
    extra_body={
        "cfg_scale": 1.0,
        "steps": 8,
        "seed": 1,
        "text_mode": True,
    },
)

print(image)

Step Plan

Integration Guide

Documentation Index

​Prerequisites

​Image Generation / Editing Models

​Supported Models

​Endpoint Paths

​Billing Instructions

​Examples

Prerequisites

Image Generation / Editing Models

Supported Models

Endpoint Paths

Billing Instructions

Examples