Model index
Tencent Hy·Hunyuan Image

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.

PreviewImage generationMultimodal

Tencent Cloud TokenHub currently lists model ID `hy-image-v3.5-preview` and still labels it Preview as of 2026-10-12. Its API guide specifies 100k-token input, up to 20 input images, and output up to 4096×4096 (4K); these are current serving-document specifications, not a separate model release.

MODEL NUMBER226
First public date
2026-09-22
Organization
Tencent Hy
Family
Hunyuan Image
01

Specifications

Only published specifications are shown.

Maximum input
100,000 tokens↗
Input modalities
Text · Image↗
Output modalities
Image↗
Status
Preview↗
02

Overview

Release dates

— Tencent introduced Hy Image 3.5 Preview for image generation and editing, with up to five references, multi-turn creation and 2K output; it remains a preview. ↗

03

Specifications alongside predecessor

Compared with HunyuanImage 3.0 ↗

PreviousHunyuanImage 3.080B · — ctx
CurrentHy Image 3.5 Preview— · — ctx
04

Architecture & capabilities

Model capabilities

Image generationImage editingText renderingComplex layoutsMulti-referenceMulti-turn editing
05

Release history

Preview

Tencent introduced Hy Image 3.5 Preview for image generation and editing, with up to five references, multi-turn creation and 2K output; it remains a preview.

View source
06

Related models

Select a card to view the related model.

07

Sources

Suggest a correction

Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.