Tencent Hunyuan releases Hy Image3.5 preview image generation model
Original title:Hy Image3.5 preview 发布:为专业创作提供高性价比模型
AI summary
Tencent Hunyuan released Hy Image3.5 preview, which supports text-to-image and image-to-image, up to 5 reference images, multi-turn editing and output at up to 2K resolution. In GSB blind tests by over a hundred professional designers, it beat the previous generation by more than 30% overall.
Key Takeaways
- Tencent Hunyuan released Hy Image3.
- 5 preview,which supports text-to-image and image-to-image,up to 5 reference images,multi-turn…
- In GSB blind tests by over a hundred professional designers,it beat the previous generation by…
Quick Facts
- Published
- Updated
- Source
- 腾讯混元:Research(API)
- Category
- Model Releases
- AI score
- 60
原文给出了文本渲染、编辑一致性与定价等具体能力细节,以及多家腾讯内部产品的实测反馈,便于评估适用场景。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Tencent Hunyuan releases Hy Image3.5 preview image generation model. September 21, 2026. https://new.nat6.net/en/news/cmuc2t8pi06v6rots79xxyyt8/