Tencent Hunyuan 3.5 Image Model Opens Free Early Access, Tested on Cinematic Lighting
HeyToha · x · 2026-09-18
Tencent's Hunyuan 3.5 (HY-image-3.5) image generation model is open for early access and free testing.
The author shares a hands-on test: in a "dark cinematic horror corridor" scene, the model captured a detailed silhouetted figure with a light source in a moody hallway, building strong atmospheric depth on floral wallpaper — and says its light cutting through darkness beats MJ V8.2.
More from Multimodal
- Local AI music: YuE2 generates a full cover song on your own machine via Pinokio — cocktailpeanut · 2026-09-19
- Runway CEO: one person made this AI film of a true story, frame costs collapsed — jnack · 2026-09-19
- Meta ships SAM 3.1 on Model API: detection, segmentation, tracking in one call — AIatMeta · 2026-09-19
- Runway's Ruby model adds alpha channel support with one-step HDR conversion — runwayml · 2026-09-19
- Midjourney --sref demo: turning Angry Birds into 1970s vintage storybook characters — michaelrabone · 2026-09-19
- Funky AI music video made with Nano Banana Pro, Kling 3 and free lip-sync tooling — cocktailpeanut · 2026-09-19