Radar / AI media tools / Tencent Hy Image 3.5 Preview
Tencent Hy Image 3.5 Preview
Tencent's latest image model with multi-turn conversational editing, direct 4K output, and up to 20 reference images.
Why it matters
First Chinese image model to combine multi-round conversational refinement with direct 4096x4096 output and 20 reference images, judged 30% better than v3.0 by professional designers, integrated into Yuanbao and Tencent Cloud.
What you could build with it
Build a brand-consistency design pipeline: feed a product's existing assets as reference images, then use multi-turn conversational edits to generate whole campaign variants (ads, posters, social) that stay visually consistent.
Does it hold up?
Too early to judge. Preview launched September 22; only one independent API walkthrough confirms it works end to end, and there are no third-party quality evaluations or real deployments yet.
Built with Tencent Hy Image 3.5 Preview
- Independent API setup and working CLI walkthroughwriteup · Third-party guide setting up the Hy Image 3.5 API with a working command-line example, confirming the preview is callable end to end.
- YouTube coverage of the preview launchvideo · Creative AI channel covering the Hy Image 3.5 preview release and its multi-turn editing claims.
- RuntimeWire API and pricing analysiswriteup · Independent analysis of the preview's multi-turn editing API, pricing, and how it compares with rival image models.
Learn more
First spotted on article: source.
More AI media tools
HyperFramesHeyGen's open-source framework that turns HTML/CSS/GSAP into deterministic MP4 video via 21 agent skills and a router…media · JEV 0.69Meshy crosses $100M ARR and launches official iOS/Android appsMeshy announced Sep 30 that ARR surpassed $100M (up 100x in under two years, first AI-3D company at that milestone)…media · JEV 0.61PixVerse R2: real-time world model with persistent, playable worldsUpgrade to PixVerse's real-time world model: a generated world keeps running live, remembers earlier user actions, and…media · JEV 0.4Hunyuan3D World Model 1.0Open-source model generating explorable, interactive 360-degree 3D worlds from text or image input.media · JEV 0.38Qwen-Image-2.17B open-weights image model with unified text-to-image generation and editing, day-0 Diffusers and ComfyUI support.media · JEV 0.34Synthesia SessionsReady-made platform for two-way conversations with lifelike AI avatars — Roleplay and Survey Sessions available now…media · JEV 0.31
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.