MODEL LINEAGE
中文
All families

FAMILY / TENCENT HY

Hunyuan Image

Tencent’s natively multimodal image-generation line for open deployment.

First model
2025
Models
3
Latest dated version
Hy Image 3.5 Preview

01 / RELEASE SEQUENCE

Family release sequence

Compare versions →
  1. 2025-09-28HunyuanImage 3.0Image generation · Reasoning
  2. 2026-01-26HunyuanImage 3.0 InstructImage generation · Multimodal
  3. 2026-09-22Hy Image 3.5 PreviewImage generation · Multimodal
3 versions
What changed ↓

02 / GENERATIONS

What changed

01

HunyuanImage 3.0

A native multimodal MoE image model with 80B total and 13B active parameters.

02

HunyuanImage 3.0 Instruct

The instruction version of HunyuanImage 3.0, adding reasoning, image editing, and multi-image fusion, separate from the original text-to-image model.

03

Hy Image 3.5 Preview

Tencent Hy’s image-generation and editing preview model supports text-to-image, image-to-image, and multi-turn editing; Tencent Cloud TokenHub’s current guide lists output up to 4K.