Sign In

Simple Txt2Img with Preview — H3 Image Workflow

Updated: Nov 17, 2026

toolminimax h3t2i

Download

1 variant available

Config Other

Simple H3Image t2i with preview.json

30.57 KB

Verified:

Type
Workflows
Stats

84

Reviews
Published

Nov 16, 2026

Base Model

MiniMax H3

Hash
AutoV2BBCB951952

The MiniMax H3 Community License Agreement’s grant excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America.

MiniMax H3

minimax_h3_image_compare.jpg

Simple Txt2Image with Preview — H3Image Workflow

A streamlined text-to-image workflow for MiniMax H3 Image, featuring live preview via tiny VAE so you can see the generation progress in real time.

Version Notes

  • v1.0plus = v1.0 + prompt enhancement + preset sampler combo

Key Features

  • Real-time preview​ — Powered by ModelPreviewOverrideKJ with taeh3_image tiny VAE (4.96 MB), no waiting until the end to see results

  • Prompt enhancement — available in v1.0plus and can be disabled manually.

  • Preset Sampler Combo​ — available in v1.0plus. for easy switching.

Tips

  • The preview node requires​ the tiny VAE file — don't skip it!

  • Default resolution is set to 4096×4096 (16 MP, 1:1 aspect). Adjust via the ResolutionSelector node.

  • euler/simple/6steps: Officially recommended settings.

  • sa_solver/sgm_uniform/5steps: If you find the image too noisy or notice excessive smoothing/smearing (especially when rendering realistic human skin), you might want to try this sampling configuration, which I personally recommend.

Required Models

minimax_h3_image_pruned_int8_convrot.safetensors

qwen3vl_32b_minimax_h3_int8_convrot.safetensors

minimax_h3_image_vae_fp16.safetensors

taeh3_image.safetensors

qwen3.5_9b_w4a8_gptq.safetensors (for prompt enhancement only)

Required Custom Nodes

  • ComfyUI-KJNodes​ — for ModelPreviewOverrideKJ,

  • rgthree-comfy​ — for Power Lora Loader, Seed

Installation

  1. Install required custom nodes via ComfyUI Manager → Custom Nodes Manager

  2. Download all models into their respective ComfyUI/models/ subfolders (see Model Links node in the workflow for paths)

  3. Download taeh3_image.safetensors into models/vae_approx/

  4. Load the workflow and queue prompt