Notice: GPT Image 2.6 Flare and Sunburst are newly launched with a limited-time 20% off, try it now
HiAPI
21:9 高调光渲染:左侧奶油色光晕留白,右侧悬浮半透明玻璃画板与虹彩光带,玻璃蚀刻发光展示名 minimax-h3-image;冰蓝青与腮红粉点缀,暖金对位高光。

MiniMax

MiniMax H3 Image

minimax-h3-image/text-to-image

MiniMax image model: text-to-image and editing with 1–16 reference images share one capability set, with output up to 4K, support for ten aspect ratios plus automatic ratio, suited to concept design, commercial visuals, and multi-style creation

Try minimax-h3-image/text-to-image

Input

Output

image
Fill in the parameters and run — results show up here.

Pricing

minimax-h3-image/text-to-image per image

Specifications Unit Price
1K $0.0129
2K $0.0129
4K $0.0393

Overview

This is a model that generates static images from text descriptions. You only need to enter a prompt to get an image that matches the description, and you can control the image's resolution tier, aspect ratio, and output format. When necessary, you can also fix the random seed so that results generated with the same prompt and settings are reproducible. It is aimed at designers, content creators, and developers who need to quickly bring ideas to life, and is suitable for creating concept art, atmospheric scene images, and various visual assets.

Key Highlights

  • Automatic prompt expansion — Submitted prompts are automatically expanded with additional details, helping to achieve richer visual expression.
  • Multiple resolution tiers available — The output resolution can be selected from three tiers: 1K, 2K, and 4K, corresponding to approximately 1, 4, and 16 megapixels.
  • Supports multiple aspect ratios — Built-in ratios from 1:1 to 21:9, plus automatic selection, adapting to different layout requirements.
  • Fixed seed for reproducibility — Set an integer seed between 0 and 2147483647 to reproduce results with the same prompt and parameters.

Capabilities

Text-to-image: Input a prompt describing the image, and the model generates a static image accordingly. Prompts must be at least 1 character and at most 5000 characters.

Resolution tier control: The output resolution can be selected from three tiers: 1K, 2K, and 4K, corresponding to approximately 1, 4, and 16 megapixels respectively; the default is 2K.

Aspect ratio control: Supports 1:1, 5:4, 4:5, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, and automatic ratio; the default is 1:1.

Output format selection: JPEG or PNG output can be selected; PNG files are larger, approximately 12 MB at 2K and approximately 30 MB at 4K.

Fixed random seed: An integer seed from 0 to 2147483647 is provided to reproduce results with the same prompt and parameters; if not set, it is randomly generated.

Use Cases

  • Concept designers drawing characters and scenes — Enter text descriptions of characters or scenes to generate stylized concept art for preliminary proposals and visual development.
  • Content creators making illustrations — Write prompts based on article or video themes to generate images that fit the layout, ready for direct use in content publishing.
  • Commercial visual asset production — Select the 4K tier and a high aspect ratio to generate high-resolution assets for advertising or presentation materials.
  • Developers generating images in batches — Use fixed seeds with parameter combinations to batch-generate reproducible image assets and integrate them into design or content pipelines.

Limitations and Selection Advice

The prompt is required, can be at most 5000 characters, and cannot contain only whitespace characters. The resolution tier, aspect ratio, and output format must each be selected from enumerated values; custom numeric values are not supported. Seed values are limited to integers from 0 to 2147483647. The generated result is a static image, with one image output per request.

  • New model MiniMax H3 Image is live: text-to-image and multi-reference editing

Frequently asked questions

View all FAQs →
  • How many reference images can be provided at most?

    Image-to-image accepts a maximum of 16 reference images and a minimum of 1. Formats are JPG, PNG, or WEBP, with each side between 128–8192 px and each image no larger than 20 MB. Each reference image costs an additional $0.0036; for example, 2K with 3 reference images costs $0.0129 + 3 × $0.0036 = $0.0237 in total. When writing prompts, refer to each image by number such as Picture 1, Picture 2 in the order they were passed in, so the model can correctly map to the objects you want to edit or combine.

  • How are the output dimensions determined, and how large can they get?

    Resolution comes in three tiers: 1K, 2K, and 4K, roughly 1 MP, 4 MP, and 16 MP respectively, with 2K as the default. Aspect ratio can be auto or 1:1, 5:4, 4:5, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9; when auto is selected, the model decides based on the prompt and reference images, so specify it explicitly if you need a fixed composition.

  • How should I write the prompt to preserve the character's appearance?

    Organize it in this order: first describe the subject you want to keep, then write the parts you want to change, and finally refer to images by number: ① Start with one or two sentences fixing the subject's appearance features, such as hairstyle, clothing, color scheme, and signature details; ② Then specify the target scene, pose, camera, and lighting; ③ When you need to reference a reference image, write "the person in Picture 1", numbering multiple images in the order they are passed in. Prompts are capped at 5000 characters; putting details in the body text is more effective than piling up adjectives.

  • How can I create multi-angle character design sheets for the same character?

    First use a clear, unobstructed reference image of the subject as Picture 1, fix the character feature description in the prompt, then generate the images one by one and change only the description of the angle or pose, for example front, side, back, half-body, and full-body, with the aspect ratio fixed at 3:4 or 1:1. Keeping the same seed for each image helps reduce random variation; the stylistic consistency of a series mainly depends on the reference image plus a fixed subject description.

Related Models

View all models →

Same Type