MiniMax H3 logoMiniMax H3

Open-weight image generation · Text to image · Reference editing

MiniMax H3 Image
Generator for 4K Creation and Editing

Create a new image from a detailed brief, or combine visual references to guide the subject, composition, style and spatial details. MiniMax H3 Image supports text-to-image generation, image editing, output up to 4K and as many as 16 reference images.

Text to ImageImage Edit
PromptText to image
Describe the subject, setting, framing, light, and style.
Aspect ratio
16:9
Resolution
1K
Format
JPEG
Seed
-1
Sign in to generate

Create images from text or edit with up to nine reference images. Sign in to use your credits.

Example image preview

Text to image · Reference editing

Example image preview showing a woman in a navy coat on a rain-wet street

Illustrative image for composition and lighting inspiration.

Image workflowMiniMax H3 Image ParametersView parameters

Review the official H3-Image inputs, sizing methods, batch controls and output formats before submitting a task.

Text to image

  • promptRequiredUp to 32,000 characters describing the complete image
  • sizeOptionalauto, or custom WIDTHxHEIGHT within the supported pixel-area and ratio limits
  • aspect_ratioOptionalA ratio from 1:3 to 3:1 when size is auto
  • areaOptional1K, 2K or 4K; the official API defaults to 4K
  • nOptionalGenerate 1 to 10 images; default 1
  • output_formatOptionaljpeg by default, or png / webp
  • disable_prompt_enhancedOptionalPrompt enhancement is enabled by default for text-to-image

Reference editing

  • promptRequiredThe intended result, including what changes and what remains fixed
  • imagesRequired1 to 16 reference images; upload order determines the Picture number
  • sizeOptionalauto, or custom WIDTHxHEIGHT within the supported limits
  • aspect_ratioOptionalA ratio from 1:3 to 3:1 when size is auto
  • areaOptional1K, 2K or 4K output-area level
  • nOptionalGenerate 1 to 10 edited images; default 1
  • output_formatOptionaljpeg by default, or png / webp

Aspect ratios from 1:3 to 3:1

1:1Square

Avatars, covers and balanced product compositions

4:5Portrait

Feed posts and editorial portraits

3:4Portrait

Character cards and print-style layouts

2:3Portrait

Photography and poster compositions

9:16Vertical

Stories, Shorts and mobile creative

1:2Tall

Mobile hero images and tall displays

1:3Tall limit

The tallest supported canvas ratio

16:9Landscape

Key art, web headers and presentation frames

4:3Landscape

Classic frames and technical boards

3:2Landscape

Camera-style compositions

5:4Landscape

Product and large-format layouts

2:1Wide

Blog headers and campaign banners

3:1Wide limit

The widest supported canvas ratio

21:9Ultrawide

Cinematic concept art and title beds

X:YCustom ratio

Any integer ratio from 1:3 to 3:1 within API limits

Three output-area levels

1KConcept iteration

Target area comparable to 1024 × 1024

2KDetailed review

Target area comparable to 2048 × 2048

4KLargest area level

Target area comparable to 4096 × 4096

Three output formats

jpegDefault

Compact delivery for photographic images

pngOptional

Lossless output for graphics and hard edges

webpOptional

Efficient delivery for modern web experiences

Output-area level
4K
Reference images
16
Prompt characters
32K
Images per request
1–10

Prompt examples

What Can You Create with MiniMax H3 Image?

Use these structures for game key art, character sheets, product concepts and spatial image edits.

01

Cinematic game key art

A lone rider pauses beside a desert waystation as a wall of dust approaches from the horizon. Worn leather gear, warm late-afternoon light, distant mesas, strong readable silhouette, cinematic game key art.

02

Character design sheet

Create a character sheet for the person in <Picture 1>. Show front, side and rear views plus three facial expressions. Keep the same proportions, costume materials and color palette across every panel.

03

Product exploded view

Create an exploded presentation view of the product in <Picture 1>. Separate the major parts along their assembly axes, keep the materials and proportions accurate, group small fasteners beside the correct component, clean dark studio background.

04

Spatial image edit

Move the chair in <Picture 1> between the two mirrors. Keep the camera position, room structure and lighting unchanged. Update both mirror reflections so they match the new chair position.

The open-weight model

What Is MiniMax H3 Image?

MiniMax H3 Image is an open-weight model for generating and editing still images. Start from text alone, or bring reference images for a subject, product, visual style, layout or environment.

The model is designed to follow layered instructions about objects, camera position, composition, lighting and visual relationships. That makes it useful for character development, game worlds, product concepts, spatial scenes and technical illustrations—not only isolated portraits.

The official API supports 1K, 2K and 4K output-area settings, prompts up to 32,000 characters, 1 to 16 reference images and batches of 1 to 10 images. Review every result for identity, text, reflections, object relationships and other details that matter to the final asset.

Image gallery

MiniMax H3 Image Examples

MiniMax H3 image creation example 1
MiniMax H3 image creation example 2
MiniMax H3 image creation example 3
MiniMax H3 image creation example 4
MiniMax H3 image creation example 5
MiniMax H3 image creation example 6

Official model capabilities

What You Can Create with MiniMax H3 Image

Create from text, combine references, edit spatial relationships and request several visual directions from one structured brief.

Supported image workflows
What you wantSupportedWhat you provide
Generate from textYesA complete brief describing the subject, composition, environment, light and intended visual style
Combine visual referencesYesUp to 16 images, with a clear role assigned to each subject, product, style or layout reference
Edit part of a sceneYesThe requested change plus explicit instructions for what must remain fixed
Build character and concept sheetsYesReference images plus directions for viewpoints, expressions, materials and panel layout
Create product and technical visualsYesA source product image plus instructions for cutaways, exploded views or labeled compositions
Generate several directionsYesA prompt, output settings and a batch size from 1 to 10 images through the official API

From a prompt alone

MiniMax H3 Text to Image

Turn a layered visual brief into one or more images at 1K, 2K or 4K, with automatic, ratio-based or custom sizing.

Follow a Layered Creative Brief

Describe the subject, environment, camera angle, layout, lighting, materials and intended use. H3 Image is designed to carry these connected instructions into one composition.

Create at 1K, 2K or 4K

Choose an output-area level or provide a custom width and height. Use smaller outputs to explore a direction, then move to 4K when the composition is ready for detailed review.

Control the Canvas Shape

Use automatic sizing, a ratio from 1:3 to 3:1, or supported custom dimensions. The API reports the actual width and height returned for every image.

Generate 1 to 10 Images

Request one focused result or a batch of alternatives. Compare the outputs for composition and detail instead of treating batch variations as guaranteed matches.

Multi-reference editing

MiniMax H3 Image Edit Features

Blend up to sixteen official-API references and describe which subjects, products, layouts, materials and scene details should change or remain fixed.

Blend Up to Sixteen References

Use one image for the subject, another for the product, another for the palette and another for the layout. Tell the model what each reference contributes to the result.

Preserve the Details That Matter

Name the identity cues, proportions, materials, accessories, colors or camera decisions that must remain recognizable after an edit.

Edit Spatial Relationships

Move or replace objects while describing how perspective, shadows and reflections should respond. Also state which parts of the room or composition must stay fixed.

Restyle and Rebuild a Scene

Turn a source into game art, animation, a technical illustration or another clearly named medium while retaining the selected subject and structural details.

Five steps

How to Use MiniMax H3 Image

Choose a workflow, assign references, write the complete brief, set the output and review every result.

  1. 01

    Choose Text to Image or Image Edit

    Begin with a written brief when you want a new composition. Choose image editing when a subject, product, style, layout or environment should come from reference images.

  2. 02

    Give Every Reference a Role

    Upload up to sixteen references through the official workflow and identify what each one controls. For example: use Picture 1 for the subject, Picture 2 for the outfit and Picture 3 for the layout.

  3. 03

    Write the Complete Visual Brief

    Describe the intended result, object relationships, camera or layout, lighting, materials and constraints. For edits, state both what should change and what must remain fixed.

  4. 04

    Set Size, Format and Batch Count

    Choose 1K, 2K or 4K, a ratio from 1:3 to 3:1, JPEG / PNG / WebP and one to ten images. Use only one sizing method when calling the official API.

  5. 05

    Review and Refine

    Inspect identity, object placement, reflections, hands, labels and unintended changes. Revise one instruction at a time and retain the version that meets the brief.

Creative and production workflows

MiniMax H3 Image Use Cases

Use H3 Image for game art, character development, product concepts, technical illustration, spatial editing and reviewed image-to-video first frames.

Image use cases
Use caseEndpointWhat it produces
Game key artText to image or referencesCharacters, environments and atmosphere combined into launch art or store banners
Character designReference editingTurnarounds, expressions, costumes and alternate scenes built around one character direction
Product conceptsReference editingStudio scenes, material studies, exploded compositions and presentation views
Technical illustrationText to image or referencesMulti-panel explanations, cutaways, labeled diagrams and visual research boards
Spatial scene editingReference editingRepositioned objects with instructions for perspective, shadows and reflections
Image-to-video preparationText to image or referencesReviewed first frames with settled subject, styling and composition

Prompt craft

How to Write MiniMax H3 Image Prompts

Structure the brief around composition, reference roles, object relationships, fixed details and short readable text.

01

Describe the Whole Composition

Name the subject, environment, camera or layout, light, materials and intended visual style so the model has a complete scene to organize.

02

Give Every Reference a Job

Explain which picture controls the subject, product, palette, style or layout instead of asking the model to infer why each image was included.

03

Describe Object Relationships

State what is in front, behind, inside, reflected by or attached to something else when spatial accuracy matters.

04

Say What Must Stay Fixed

For edits, preserve specific identity cues, proportions, camera position, architecture, materials or colors instead of only describing the new element.

05

Keep Generated Text Short

Use concise titles and labels inside the image. Add long paragraphs later in a design tool, where typography can be checked and edited directly.

Common failures and the fix

Image prompt troubleshooting
What you getWhyFix
The composition misses part of the briefThe prompt lists objects but not their relationshipsDescribe placement, scale, viewpoint and which details have priority
The wrong reference controls the resultThe references were not assigned clear rolesIdentify Picture 1, Picture 2 and each additional reference explicitly
Unrequested parts of the image changedThe edit describes only the new elementState which subject, camera, layout, colors and materials must remain fixed
Reflections or shadows are inconsistentThe prompt changes an object without updating its spatial effectsDescribe how the new position should affect reflections, contact shadows and lighting
Text is misspelled or too denseThe image contains more copy than can be reliably reviewedKeep generated text short and add longer copy in a design tool afterward

Same account, different job

Images or Video: Which One You Need

The difference is what you hand over and what you get back. Choose a still for the look, or a clip for motion and sound.

Image editing and video generation compared
WorkflowImage editingVideo generation
What you supplyA prompt and optionally 1–16 reference imagesA prompt, first frame or multimodal reference pack
What comes back1–10 still images through the official APIA timed clip with motion and audio
Output1K, 2K or 4K area levelsResolution and duration depend on the selected video model
Best forConcepts, key art, characters, products and reviewed first framesMotion, camera movement, performance and sound
Recommended orderSettle the visual direction firstAnimate the approved still after the composition is ready

A common order of work is to settle the look first, including outfit, styling and location, then take the approved still into the video generator as a first frame.

Frequently asked questions

MiniMax H3 Image FAQ

Official specifications for 4K output, sixteen references, batch generation, sizing, prompt enhancement, formats and open weights.

What is MiniMax H3 Image?

MiniMax H3 Image is an open-weight model for text-to-image generation, reference-based creation and image editing. It is designed to follow detailed creative instructions involving subjects, objects, composition, lighting and spatial relationships.

What resolutions does MiniMax H3 Image support?

The official API supports 1K, 2K and 4K output-area settings. It also accepts supported custom width and height values when the total pixel area and aspect ratio remain within the documented limits.

How many reference images can MiniMax H3 Image use?

The official image-editing API accepts 1 to 16 reference images. Upload order determines the Picture number, so prompts can assign a clear role to each reference.

Can MiniMax H3 Image generate several images at once?

Yes. The official API supports batches of 1 to 10 images per request. Individual results can still differ, so review every output rather than assuming the batch is internally identical.

What aspect ratios does MiniMax H3 Image support?

When using automatic sizing, the official API accepts integer X:Y ratios from 1:3 to 3:1. You can also provide supported custom width and height values instead of an aspect ratio and area level.

How long can a MiniMax H3 Image prompt be?

The official API accepts prompts up to 32,000 characters. A longer limit is useful for structured briefs, but the prompt should still make priorities, object relationships and constraints easy to identify.

Does MiniMax H3 Image enhance prompts automatically?

Text-to-image prompt enhancement is enabled by default and can be disabled. Image editing always applies prompt enhancement. The official response can include the revised prompt used for each image.

What output formats are available?

The official API returns JPEG by default and also supports PNG and WebP. Choose the format according to the final workflow rather than expecting the format alone to improve image detail.

Is MiniMax H3 Image open source?

MiniMax describes H3 Image as an open-weight model. Developers should review the official model license and usage restrictions before local deployment, redistribution or commercial integration.

Can MiniMax H3 Image results be used for video?

Yes. After reviewing the still for subject, composition and detail, use it as a first frame in an image-to-video workflow and describe the intended subject and camera movement.

Get started

Create Your First MiniMax H3 Image

Start from a written idea or bring visual references. Build the composition, review the details and refine the image until it fits your project.