MiniMax-H3-ImageOnline APIUse MiniMax-H3-Image directly via API.<ul><li>Global: <a target="_blank" rel="noopener noreferrer nofollow" href="http://platform.minimax.io">platform.minimax.io</a> | CN: <a target="_blank" rel="noopener noreferrer nofollow" href="http://platform.minimax.cn">platform.minimax.cn</a></li></ul>API docs:<ul><li>Text-to-image: <a target="_blank" rel="nofollow" href="https://platform.minimax.io/docs/api-reference/image-generation-h3-generations">EN-docs</a>, <a target="_blank" rel="nofollow" href="https://platform.minimax.cn/docs/api-reference/image-generation-h3-generations">CN-docs</a></li><li>Image editing: <a target="_blank" rel="nofollow" href="https://platform.minimax.io/docs/api-reference/image-generation-h3-edits">EN-docs</a>, <a target="_blank" rel="nofollow" href="https://platform.minimax.cn/docs/api-reference/image-generation-h3-edits">CN-docs</a></li><li>Prompt expansion: <a target="_blank" rel="nofollow" href="https://platform.minimax.io/docs/api-reference/image-generation-h3-context-ir">EN-docs</a>, <a target="_blank" rel="nofollow" href="https://platform.minimax.cn/docs/api-reference/image-generation-h3-context-ir">CN-docs</a></li></ul>Online AppUse MiniMax-H3-Image directly via App.<ul><li>WebApp Global: <a target="_blank" rel="noopener noreferrer nofollow" href="http://hailuoai.video">hailuoai.video</a> | CN: <a target="_blank" rel="noopener noreferrer nofollow" href="http://hailuoai.com">hailuoai.com</a></li><li>Desktop Global: <a target="_blank" rel="noopener noreferrer nofollow" href="http://agent.minimax.io">agent.minimax.io</a> | CN: <a target="_blank" rel="noopener noreferrer nofollow" href="http://agent.minimax.cn">agent.minimax.cn</a></li></ul>IntroductionMiniMax-H3-Image is a state-of-the-art open-source model for image generation and editing from the <a target="_blank" rel="nofollow" href="https://huggingface.co/MiniMaxAI/MiniMax-H3">MiniMax H3</a> family. It combines intelligent understanding of creative intent with the ability to build visual worlds: with precise instruction following, it develops a creative concept into concrete characters, scenes and atmosphere. Generation and editing are unified in one checkpoint, which generates images from text (text-to-image) and edits one or more reference images (image editing), giving creators and developers a flexible and controllable way to create images.It generates images of about 16 megapixels at every aspect ratio, from 4096x4096 (1:1) to 6272x2688 (21:9), directly and without an upscaler (see <a target="_blank" rel="nofollow" href="https://huggingface.co/MiniMaxAI/MiniMax-H3-Image#sizes">Sizes</a>). The checkpoint is distilled to 6 sampling steps (6 NFEs) with no classifier-free guidance. Its diffusion transformer (DiT) has the H3 architecture without the audio layers, and it uses the MiniMax-H3 text encoder unchanged.HighlightsMiniMax-H3-Image brings together three core strengths: speed, image quality, and instruction following.<ol><li>16-megapixel images at a practical computational cost. Compared with the 1–4 MP outputs common today, 16 MP (4096 × 4096) images offer far more detail but typically require substantially more computation. MiniMax-H3-Image keeps that computational cost manageable, making 16 MP generation practical for everyday creation.</li><li>Rich detail. Remarkable realism. MiniMax-H3-Image goes beyond the familiar “AI look” to produce images with intricate detail and lifelike realism, opening up more possibilities for creative and professional use. It brings generated imagery closer to the richness and nuance of the real visual world.</li><li>Stronger instruction following. Greater creative control. Great image generation goes beyond beautiful pictures—it helps creators bring their ideas to life. MiniMax-H3-Image delivers the strongest instruction following among open-source models and supports up to 16 reference images, giving creators more control over the final result.</li></ol>

MiniMax-H3-Image

MiniMax H3 image, Open Weights
Hailuo AI API MiniMax Website GitHub Hugging Face
ModelScope MiniMax AI WeChat Discord LICENSE

MiniMax-H3-Image
Online API
Use MiniMax-H3-Image directly via API.

Global: platform.minimax.io | CN: platform.minimax.cn
API docs:

Text-to-image: EN-docs, CN-docs
Image editing: EN-docs, CN-docs
Prompt expansion: EN-docs, CN-docs
Online App
Use MiniMax-H3-Image directly via App.

WebApp Global: hailuoai.video | CN: hailuoai.com
Desktop Global: agent.minimax.io | CN: agent.minimax.cn
Introduction
MiniMax-H3-Image is a state-of-the-art open-source model for image generation and editing from the MiniMax H3 family. It combines intelligent understanding of creative intent with the ability to build visual worlds: with precise instruction following, it develops a creative concept into concrete characters, scenes and atmosphere. Generation and editing are unified in one checkpoint, which generates images from text (text-to-image) and edits one or more reference images (image editing), giving creators and developers a flexible and controllable way to create images.

It generates images of about 16 megapixels at every aspect ratio, from 4096x4096 (1:1) to 6272x2688 (21:9), directly and without an upscaler (see Sizes). The checkpoint is distilled to 6 sampling steps (6 NFEs) with no classifier-free guidance. Its diffusion transformer (DiT) has the H3 architecture without the audio layers, and it uses the MiniMax-H3 text encoder unchanged.

Fifteen MiniMax-H3-Image text-to-image results in landscape and portrait formats: a 3D fantasy battle, a blue-green landscape painting, a tree frog, an indigo-dyed rabbit, a 3D white-haired girl, a portrait among flowers, a sci-fi city, dumplings, a highland cow, a mirror portrait, a 3D otter and sheep, a pixel art cat, a jewel beetle, giant cherries and a fisheye selfie

Highlights

MiniMax-H3-Image brings together three core strengths: speed, image quality, and instruction following.

16-megapixel images at a practical computational cost. Compared with the 1–4 MP outputs common today, 16 MP (4096 × 4096) images offer far more detail but typically require substantially more computation. MiniMax-H3-Image keeps that computational cost manageable, making 16 MP generation practical for everyday creation.
Rich detail. Remarkable realism. MiniMax-H3-Image goes beyond the familiar “AI look” to produce images with intricate detail and lifelike realism, opening up more possibilities for creative and professional use. It brings generated imagery closer to the richness and nuance of the real visual world.
Stronger instruction following. Greater creative control. Great image generation goes beyond beautiful pictures—it helps creators bring their ideas to life. MiniMax-H3-Image delivers the strongest instruction following among open-source models and supports up to 16 reference images, giving creators more control over the final result.


Files with SHA256: 83eb140f1ff95c068f8a6886e6d3f3d0d4ab2e07bb2fe6d2ef992a51146ee622