MiniMax H3 Image Text-to-Image Workflow

MiniMax H3 Image is a high-resolution image generation model that works best between 4 MP and 20 MP. In this guide you’ll learn how to generate images from text in ComfyUI using the official MiniMax H3 Image workflow.

MiniMax H3 Image Official Page

• https://huggingface.co/MiniMaxAI/MiniMax-H3-Image

Instructions

1. Update to the latest version of ComfyUI.
2. Download the model files linked below and copy them to the locations shown.
3. Download the workflow and drag it into ComfyUI.
4. Update the prompt text.
5. Click the Run button, your image will be generated.
6. If you have any problems then leave a comment on the YouTube video and I can help you out.

Workflow

• minimax-h3-image-t2i.json

Models

Download these files:

• minimax_h3_image_pruned_int8_convrot.safetensors (21 GB)
• qwen3vl_32b_minimax_h3_int8_convrot.safetensors (25.28 GB)
• minimax_h3_image_vae_fp16.safetensors (1.17 GB)

Place them in these folders:

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── minimax_h3_image_pruned_int8_convrot.safetensors
│   ├── 📂 text_encoders/
│   │   └── qwen3vl_32b_minimax_h3_int8_convrot.safetensors
│   └── 📂 vae/
│       └── minimax_h3_image_vae_fp16.safetensors

Prompt Expansion Guide

• Official prompt guide: https://github.com/MiniMax-AI/MiniMax-H3-Image/blob/main/skills/h3-image-prompt-writing/references/t2i-en.txt