Tencent's Unreleased Hunyuan 3.5 Image Model Spotted in Early Access, Pitted Against GPT Image-2
FellMentKE · x · 2026-09-19
An early-access version of Tencent's unreleased Hunyuan 3.5 (HY-IMAGE-3.5) has surfaced on OnSolo, and hands-on testing of its image generation looks impressive.
- Samples span detailed classical artwork with intricate floral patterns and figures, dark stylized compositions, and portrait-style imagery
- Tencent's own video places HY-IMAGE-3.5 side by side with GPT Image-2 for a visual comparison
- OnSolo members can currently try Hunyuan 3.5 for free ahead of the official release
More from Multimodal
- Meta ships SAM 3.1 on Model API: noun-phrase prompts for detection, segmentation and tracking at $2.50/1k images — armand_ruiz · 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