Tencent launches HunyuanImage 3.5 preview with 2K images at 0.15 yuan each, cheapest among 13 models
智东西 · wechat · 2026-09-22
Tencent's Hunyuan team released HunyuanImage 3.5 preview, a new image generation model supporting text-to-image, image-to-image, and multi-turn conversational editing with up to 5 reference images and 2K resolution output.
- In an internal GSB blind test with hundreds of professional designers, it improved 30% over HunyImage 3.0, matching ByteDance's Seedream 5.0 Pro and slightly beating Nano-Banana Pro and Qwen-Image 3.0 Pro.
- It is already integrated into multiple Tencent products including Yuanbao, ima, WorkRally, OnSolo, and Miora; during a two-month gray rollout in Yuanbao, image generation requests rose over 50%.
- The API is live on Tencent Cloud TokenHub at 0.15 yuan per 2K image, charging only for final outputs—the lowest per-image cost among 13 mainstream models (GPTImage 2.5 low 0.162 yuan, Qwen-Image 3.0 0.2 yuan).
- Tencent merged its Hunyuan LLM and multimodal teams into a Foundation Models unit under Yao Shunyu in July, and has hired multimodal researchers including Yonglong Tian (ex-OpenAI).
The piece argues that with generation quality gaps narrowing, pricing, product entry points, and integration into real creative workflows are becoming the next battleground.
More from Multimodal
- Endless screensaver of self-assembling quantum cryostats, made with Gemini 4 Carbon — hapticdata · 2026-11-12
- ADM 3 Cloud ranks #47 of 80 at photo enhancement and restoration — ArtificialAnlys · 2026-11-12
- Apple's ADM 3 Cloud tested: #42 at image editing, #85 at text-to-image — ArtificialAnlys · 2026-11-12
- Object-level edits are ADM 3 Cloud's strongest skill, ranking #27 of 80 — ArtificialAnlys · 2026-11-12
- Apple's ADM 3 Cloud image model ranks #42 in editing and #85 in text-to-image on Artificial Analysis arena — ArtificialAnlys · 2026-11-12
- Adobe Firefly debuts Story Builder tool for streamlined visual storytelling — LudovicCreator · 2026-11-12