Microsoft Mai Image 2.5 Text To Image

Microsoft Mai Image 2.5 Text To Image

Playground

Microsoft MAI Image 2.5 Text-to-Image is a fast AI image generation model that creates photorealistic, design-ready images from text prompts with strong realism, typography, and stylized visual control. Ready-to-use REST inference API for creative design, marketing visuals, product mockups, brand assets, social media content, concept art, and professional text-to-image workflows with simple integration, no coldstarts, and affordable pricing.

Features

Microsoft MAI Image 2.5 Text-to-Image

Microsoft MAI Image 2.5 Text-to-Image generates images from natural-language prompts with a simple workflow for prompt input, size selection, and output format control. It is suitable for concept art, marketing visuals, social media content, product mockups, and other prompt-driven image generation workflows.

Why Choose This?

• Prompt-based image generation Turn natural-language descriptions into polished visual outputs.

• Simple parameter set Use a lightweight workflow with prompt, size, and output format controls.

• Flexible output sizing Choose the output size preset that best matches your intended composition.

• Multiple output formats Export generated images in supported formats such as png.

• Production-ready API Suitable for creative ideation, campaign visuals, concept generation, and content production workflows.

Parameters

How to Use

1. Write your prompt — describe the subject, style, lighting, composition, and mood you want.
2. Choose the size (optional) — select the output framing that fits your use case.
3. Choose the output format (optional) — select the file format that best fits your workflow.
4. Submit — run the model and download the generated image.

Example Prompt

A cinematic movie still of an adult US woman standing alone on a rainy city street at night, wet pavement reflecting neon lights, long black coat, calm but emotional expression, soft bokeh background, realistic rain, shallow depth of field, dramatic cinematic lighting, photorealistic, no text

Pricing

Pricing includes a fixed base image charge plus a small surcharge based on prompt length.

Billing Rules

• Base price is $0.05 per image
• Prompt-length surcharge is $0.0001 for every started 10 characters
• size and output_format do not affect pricing

Best Use Cases

• Concept art — Explore visual ideas and art directions quickly.
• Marketing creatives — Generate ad concepts, banners, and campaign visuals.
• Social media content — Create prompt-driven imagery for posts and promotions.
• Product mockups — Produce visual concepts for products, packaging, or branded scenes.
• Creative prototyping — Iterate rapidly on different visual directions.

Pro Tips

• Be specific in your prompt about subject, environment, lighting, and style.
• Shorter prompts are cheaper, while longer prompts can provide more control.
• Use clear style cues such as cinematic, editorial, photorealistic, minimal, or painterly when needed.
• Start with a compact prompt and only add more detail if the result needs stronger direction.
• Choose png when you want better image quality for downstream editing.

Notes

• prompt is required.

• Pricing includes a fixed base image charge and a prompt-length surcharge.

• Better prompts usually improve output quality and consistency.

Related Models

• Other MAI image generation workflows — Useful when you need different quality, speed, or control trade-offs.
• Prompt-based image generation models — Useful when you want alternative visual styles or model behavior.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/microsoft/mai-image-2.5/text-to-image" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1:1",
    "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}"