Microsoft MAI Image 2.5 Edit API

Microsoft MAI Image 2.5 Edit

Microsoft MAI Image 2.5 Edit edits an input image using natural-language instructions, with support for optional aspect-ratio control and multiple output formats. It is suitable for image refinement, style changes, composition adjustments, product visuals, and other prompt-driven image editing workflows.

Why Choose This?

Prompt-based image editing
Edit an existing image by describing the changes you want in natural language.
Simple editing workflow
Upload one image, write an instruction, choose the output ratio, and generate the result.
Flexible output framing
Use size to keep the original image ratio or switch to a different preset aspect ratio.
Multiple output formats
Export results as jpeg, png, or webp.
Production-ready API
Suitable for product image refinement, visual cleanup, style changes, and creative variations.

Parameters

Parameter	Required	Description
prompt	Yes	The instruction describing how to edit the input image. Supports `3–5000` characters.
image	Yes	The image to edit. Provide an uploaded image or a public image URL.
size	No	Output aspect ratio. Supported values: `auto`, `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`. Default: `auto`.
output_format	No	The format of the edited image. Supported values: `jpeg`, `png`, `webp`. Default: `png`.

How to Use

Upload your image — provide the source image you want to edit.
Write your prompt — describe what should change and what should stay consistent.
Choose size (optional) — keep auto to preserve the original framing, or select a preset ratio.
Choose output format (optional) — select jpeg, png, or webp.
Submit — run the model and download the edited image.

Example Prompt

Turn this product photo into a premium studio advertisement with soft cinematic lighting, a clean neutral background, realistic reflections, and polished commercial styling.

Pricing

Pricing includes a fixed base edit charge plus a small additional processing fee based on prompt length and internal image-token processing.

Billing Rules

Every request starts with a base price of $0.05 per image
There is an additional processing charge that increases with prompt length
The processing charge is billed in small $0.0001 increments
size and output_format do not affect pricing

Example Costs

Prompt Length	Total Cost
10 chars	$0.0583
100 chars	$0.0592
500 chars	$0.0632
1000 chars	$0.0682
5000 chars	$0.1082

Best Use Cases

Product photo refinement — Upgrade product shots for ads, listings, and brand materials.
Style changes — Rework an image into a new visual style or mood.
Composition adjustments — Use aspect-ratio controls to adapt the edit for different formats.
Marketing creatives — Produce polished visuals for campaigns, social media, and presentations.
Creative variations — Generate multiple prompt-driven directions from the same source image.

Pro Tips

Be specific about what should change and what should stay the same.
Use auto size when you want to preserve the original image framing.
Keep prompts concise when you want lower cost and tighter control.
Use png when image quality matters more than file size.
Longer prompts may improve direction, but they also increase cost.

Notes

Both prompt and image are required.
size defaults to auto.
output_format defaults to png.
Pricing includes a fixed base edit charge and an additional prompt-sensitive processing fee.
Better prompts usually improve both edit quality and consistency.

Related Models

Microsoft MAI Image 2.5 Text-to-Image — Generate images directly from prompts.

Mai Image 2.5 Edit API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.5/edit with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Mai Image 2.5 Edit below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.5/edit" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "size": "auto",
    "output_format": "png"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("microsoft/mai-image-2.5/edit", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://example.com/your-input.jpg",
        "size": "auto",
        "output_format": "png"
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "microsoft/mai-image-2.5/edit",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "size": "auto",
    "output_format": "png"
}
)

print(output["outputs"][0])  # → URL of the generated output

Mai Image 2.5 Edit API — Frequently asked questions

What is the Mai Image 2.5 Edit API?

Mai Image 2.5 Edit is a Microsoft model for image editing, exposed as a REST API on WaveSpeedAI. Microsoft MAI Image 2.5 Edit is a fast AI image editing model that transforms input images with natural-language instructions while preserving strong realism, typography, and visual detail. Ready-to-use REST inference API for photo editing, product image updates, marketing assets, brand visuals, typography-aware edits, creative retouching, and professional image editing workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Mai Image 2.5 Edit API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/microsoft/microsoft-mai-image-2.5-edit.

How much does Mai Image 2.5 Edit cost per run?

Mai Image 2.5 Edit starts at $0.050 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Mai Image 2.5 Edit accept?

Key inputs: `prompt`, `image`, `size`, `output_format`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/microsoft/microsoft-mai-image-2.5-edit.

How do I get started with the Mai Image 2.5 Edit API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Mai Image 2.5 Edit outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Microsoft). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

サンプルすべて表示

関連モデル

README