Tencent Launches Hunyuan Image 3.5 Preview at ¥0.15 per 2K Image
腾讯混元 · wechat · 2026-09-22
Tencent released Hunyuan Image 3.5 preview, a cost-efficient professional image generation model supporting text-to-image, image-to-image with up to 5 reference images, multi-turn editing, and 2K output. In internal GSB blind tests with hundreds of designers it matched Seedream 5.0 Pro and slightly beat Nano-Banana Pro and Qwen-Image-3.0 Pro, improving 30% over HyImage 3.0. Priced at ¥0.15 per 2K image via Tencent Cloud API (output images only), it's already live in Yuanbao (image requests +50% during grayscale, portrait editing +100%), WorkRally, OnSolo, Miora, WorkBuddy, ima and Tencent Ads.
Related event: Tencent Hunyuan Rolls Out Hy Image3.5 Preview with Cheap 2K Generation(4 posts)→
More from Multimodal
- AI-generated dark fantasy series Awalon retells King Arthur legend — Kyrannio · 2026-09-22
- MiniMax H3 Turns a Mac Desktop Into Oggy-Style Cartoon Chaos — Full Prompt Included — SimplyAnnisa · 2026-09-22
- Striking human-motion visualizations made with Sentinel — Kyrannio · 2026-09-22
- New Pika impresses early users as the video startup returns to form — Kyrannio · 2026-09-22
- Museum statue meme generated with AI — prompt included — umesh_ai · 2026-09-22
- Princeton's VideoGen-Agent Adds 19 Points via Agentic RL Tool Use for Video — princetonu · 2026-09-22