# MiniMax-H3-Image ## Online API Use MiniMax-H3-Image directly via API. - Global: [platform.minimax.io](https://platform.minimax.io/docs/guides/image-generation) | CN: [platform.minimax.cn](https://platform.minimax.cn/docs/guides/image-generation) API docs: - Text-to-image: [EN-docs](https://platform.minimax.io/docs/api-reference/image-generation-h3-generations), [CN-docs](https://platform.minimax.cn/docs/api-reference/image-generation-h3-generations) - Image editing: [EN-docs](https://platform.minimax.io/docs/api-reference/image-generation-h3-edits), [CN-docs](https://platform.minimax.cn/docs/api-reference/image-generation-h3-edits) - Prompt expansion: [EN-docs](https://platform.minimax.io/docs/api-reference/image-generation-h3-context-ir), [CN-docs](https://platform.minimax.cn/docs/api-reference/image-generation-h3-context-ir) ## Online App Use MiniMax-H3-Image directly via App. - WebApp Global: [hailuoai.video](https://hailuoai.video/) | CN: [hailuoai.com](https://hailuoai.com/) - Desktop Global: [agent.minimax.io](https://agent.minimax.io/) | CN: [agent.minimax.cn](https://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](https://huggingface.co/MiniMaxAI/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](#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](assets/showcase_hero.jpg) **Highlights** MiniMax-H3-Image brings together three core strengths: speed, image quality, and instruction following. 1. **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. 2. **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. 3. **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. ## Model Zoo | Model | Role | Precision | Size | Hugging Face | | --- | --- | --- | --- | --- | | **MiniMax-H3-Image** | Text-to-image and image editing | BF16 (DiT) | 68.65 GB | [MiniMaxAI/MiniMax-H3-Image](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image) | | **MiniMax-H3-Image-PE** (optional) | Prompt expander for text-to-image | NVFP4 | 17.9 GB | [MiniMaxAI/MiniMax-H3-Image-PE](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image-PE) | ## Model Architecture MiniMax-H3-Image follows the H3-Base design with the audio branch removed. The text prompt and the reference images are encoded by the H3 text encoder; the reference images are also encoded by the image VAE. All tokens form one packed sequence for a single-stream transformer, which predicts the latent of the target image. The VAE decodes that latent into the image. - **Text encoder**: the full Qwen3-VL text encoder of MiniMax-H3, unchanged. The DiT reads the hidden states of its 50th layer. - **Image VAE**: a CNN encoder and a 2D ViT decoder (24 layers), with 16x spatial downsampling and 24 latent channels. The DiT patchifies the latent with a 2x2 patch, so each transformer token covers 32x32 pixels. - **Diffusion transformer**: 33.1B parameters, a dense single-stream transformer with 50 layers (hidden size 5376, 56 attention heads, FFN size 14336) and 3D multimodal RoPE, the same as the H3-Omni-Transformer. The weights are BF16; the embedding, timestep and output layers are FP32. ## Quick Start ### Download | Component | Content | Size | | --- | --- | --- | | `transformer/` | DiT: BF16, with the embedding, timestep and output layers in FP32. | 66.28 GB | | `pdd_fused_heads.safetensors`, `pdd_config.json` | The per-step output heads that replace the transformer's output layer, and the sampling schedule. | 12 MB | | `vae/` | Image VAE, FP32. | 2.34 GB | | `tokenizer/`, `processor/` | Qwen3-VL tokenizer and processor, identical to MiniMax-H3. | 23 MB | | Text encoder | Not in this repository. `model_index.json` loads it from [`MiniMaxAI/MiniMax-H3`](https://huggingface.co/MiniMaxAI/MiniMax-H3), folder `text_encoder/`. If you already have MiniMax-H3, it is not downloaded again. | 66.7 GB | ```text MiniMax-H3-Image/ ├── model_index.json ├── pdd_config.json ├── pdd_fused_heads.safetensors ├── processor/ ├── tokenizer/ ├── transformer/ └── vae/ ``` Download this repository and the MiniMax-H3 text encoder into the Hugging Face cache: ```bash hf download MiniMaxAI/MiniMax-H3-Image hf download MiniMaxAI/MiniMax-H3 --include "text_encoder/*" # optional prompt expander hf download MiniMaxAI/MiniMax-H3-Image-PE ``` ### Local Deployment We recommend the following inference frameworks to serve the model: - [SGLang](https://docs.sglang.io/) - see [cookbook](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3-Image) - [vLLM-Omni](https://github.com/vllm-project/vllm-omni) - see [vllm-omni recipe](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3-Image) - [diffusers](https://github.com/huggingface/diffusers) - see [diffusers docs](https://huggingface.co/docs/diffusers/main/en/api/pipelines/minimax_h3_image) - [ComfyUI](https://github.com/Comfy-Org/ComfyUI) - see [Comfy tutorial](https://docs.comfy.org/tutorials/image/minimax/minimax-h3-image); use [T2I template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_minimax_h3_image_t2i.json) / [Edit template](https://github.com/Comfy-Org/workflow_templates/blob/main/templates/image_minimax_h3_image_edit.json) #### vLLM-Omni Deployment See the [vLLM-Omni recipe](https://recipes.vllm.ai/MiniMaxAI/MiniMax-H3-Image) for per-hardware deployment configurations and measured latency. Both NVIDIA and AMD accelerators are supported, including NVIDIA H200, RTX PRO 6000 Blackwell, AMD Instinct MI350X and more. Start the server on one GPU: ```bash vllm serve MiniMaxAI/MiniMax-H3-Image --omni --host 0.0.0.0 --port 8000 ``` For lower latency, split each request over several GPUs with sequence parallelism (Ulysses), for example on 4 GPUs: ```bash vllm serve MiniMaxAI/MiniMax-H3-Image --omni --host 0.0.0.0 --port 8000 \ --num-gpus 4 --usp 4 --text-encoder-tp-size 4 ``` #### SGLang Deployment Here we use SGLang as a deployment example. See the [MiniMax-H3-Image deployment guide](https://docs.sglang.io/cookbook/diffusion/MiniMax/MiniMax-H3-Image) for additional deployment configurations. Start the server on one GPU: ```bash sglang serve --model-path MiniMaxAI/MiniMax-H3-Image --host 0.0.0.0 --port 30000 --warmup-mode off ``` To use a local copy of the MiniMax-H3 `text_encoder/` folder instead of the Hugging Face cache, add `--text-encoder-path `. For lower latency, split each request over several GPUs with sequence parallelism (Ulysses), for example on 4 GPUs: ```bash sglang serve --model-path MiniMaxAI/MiniMax-H3-Image --host 0.0.0.0 --port 30000 --warmup-mode off \ --num-gpus 4 --ulysses-degree 4 ``` #### Request parameters Text-to-image requests are JSON sent to `/v1/images/generations`. Image editing requests send the reference images as multipart form data to `/v1/images/edits`; their order defines `

Left: t2i.png from local SGLang with the enhanced prompt. Right: api_t2i.png from the MiniMax API. Both show an overhead farm-to-table feast with bread, vegetables and cheeses on a weathered wooden table

Files with SHA256: c07093a098e3bef4d43cd29c33e239a0c45424c5ff40dfcc864df00b8d664738