HunyuanImage 3.0

Tencent's open image model, competitive with the Flux and Qwen open tiers. Heavy hardware requirements compared to Z-Image for a similar result.

MAKER

Tencent

ACCESS

open-weights

TRAINABLE

Yes

GEOMETRY

3 / 5

Tasks

Text to Image

Image to Image

Available in these tools

ComfyUI

The node runtime most open-weight model work passes through. Free and runs on your own hardware, which is the whole argument — and it asks for a GPU and real setup time in return.

PUBLICATION

ArchitectureLM

SUBJECT

AI in architecture

NEWSLETTER

Weekly, free

CONTACT

hello@architecturelm.com

Contact

Privacy

Acceptable Use

Terms