Qwen3.8-27B launches on Tinker with native video support
simonguozirui · x · 2026-08-20
Qwen3.8-27B is now live on Tinker. It features native multimodal support for images and video, flexible thinking control, and improved performance in coding, professional work, research, and long-horizon agentic tasks.
More from Multimodal
- Designer builds luxury cosmetics ad locally with InvokeAI; full workflow shared — Masha-AI · 2026-08-20
- Using GPT Images 2.0 to generate consistent multi-flavor ads — GCWebDesigner · 2026-08-20
- GPT Images 2.0 generates full brand campaign assets in one prompt — GCWebDesigner · 2026-08-20
- CrossView-Warp V2: Camera Control LoRA & Node Released — DryDream6994 · 2026-08-20
- KRAFTON releases Raon-OpenTTS-1B, an open zero-shot voice cloning model — victormustar · 2026-08-20
- GPT-Image2 Workflow: Dynamic Brand Posters for Drinks and Pastries — GCWebDesigner · 2026-08-20