Microsoft Mai Image 2.5 Edit

Microsoft Mai Image 2.5 Edit

Playground

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.

Features

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

How to Use

1. Upload your image — provide the source image you want to edit.
2. Write your prompt — describe what should change and what should stay consistent.
3. Choose size (optional) — keep auto to preserve the original framing, or select a preset ratio.
4. Choose output format (optional) — select jpeg, png, or webp.
5. 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

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.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.5/edit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "auto",
    "output_format": "png"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"