MiniMax H3 Highspeed Image Advanced
MiniMax H3 Highspeed Image Advanced is the faster H3 Image with every control: edit or combine up to 16 images, set 1K to 4K or an exact size, and control prompt expansion.
## Overview
MiniMax H3 Highspeed Image Advanced is the high-speed version of H3 Image with the full set of controls. Generate an image from a prompt, edit one image, or combine up to 16 input images into one result, with an exact output size and a choice of whether the prompt is expanded.
## What you can build
- Fast compositions that combine a subject, a scene and a style from different images
- Quick edits such as recolors, background swaps and material changes
- Images at an exact size for layouts, banners or print
- Many variations of one idea for exploration
## Inputs
- A prompt describing the image to create, or the change to make and what must stay the same (up to 4,096 characters; longer text is cut). Refer to input images as Image 1, Image 2 and so on, in upload order.
- Up to 16 optional input images (JPEG, PNG or WebP), each 128 to 8,192 pixels per side. Without an image, the model generates from the prompt.
- An aspect ratio: auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9 or 9:21. With an input image, auto keeps its ratio; without one, auto uses 16:9.
- A resolution: 1K, 2K or 4K (about 1024×1024, 2048×2048 or 4096×4096 pixels, shaped to the aspect ratio).
- An optional exact width and height in pixels, used instead of the aspect ratio and resolution. Width × height must be 655,360 to 20,000,000 pixels, with a ratio between 1:3 and 3:1.
- The number of images to generate, from 1 to 10.
- The output format: JPEG, PNG or WebP.
- Prompt expansion on or off. When on, the prompt is rewritten into a detailed description before generation. Edits with input images always use it. Turning it off needs a width and height, or an aspect ratio other than auto.
## Outputs
- One to ten images in the chosen format, at the chosen size.
## Recommended settings
- With several input images, say which image provides what.
- Turn prompt expansion off when your prompt is already detailed and should be used as written.
- Use an exact width and height when you need a fixed canvas.
## Limitations
- No mask-based editing and no transparent backgrounds.
- Sizes outside 655,360 to 20,000,000 pixels, or ratios beyond 1:3 and 3:1, aren't accepted.
- Small text, logos and fine details can drift; check the results.
## Safety & compliance
- MiniMax runs content safety checks and may block a request or an image.
- Only upload images you have the right to use, and get consent before editing photos of identifiable people.
Example prompts
Great starting points for h3 highspeed image advanced.
API quick start
Run h3 highspeed image advanced with a single API call.
{
"prompt": "Turn the latte art in the cup into a deta…",
"inputImage": "https://your-cdn.com/input.png",
"aspectRatio": "auto",
"resolution": "1K"
}curl -X POST "https://api.wiro.ai/v1/Run/minimax/h3-highspeed-image-advanced" \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_WIRO_API_KEY" \
--data-binary @- <<'JSON'
{
"prompt": "Turn the latte art in the cup into a deta…",
"inputImage": "https://your-cdn.com/input.png",
"aspectRatio": "auto",
"resolution": "1K"
}
JSONOther models you might like
Explore similar image generation models.
