Alibaba Releases Multimodal Model Qwen3.8-Flash-Next on Hugging Face
Qwen · hf · 2026-08-26
Alibaba's Qwen team released Qwen3.8-Flash-Next on Hugging Face. The model features an image-text-to-text pipeline, supports multimodal conversation, and is compatible with safetensors and API endpoints.
More from Multimodal
- AI 3D workflow: generate parts with Tripo, let an agent assemble, rig and animate in Blender via MCP — majidmanzarpour · 2026-08-26
- AI-generated Demon Slayer battle pits Tengen against a female Akaza — eyishazyer · 2026-08-26
- Hyper-Real Mumbai Food Vlog Generated by Wan 3 — CurieuxExplorer · 2026-08-26
- FLORA launches MCP integration to power Claude and Cursor with multimodal agents — round · 2026-08-26
- CLSS: closed-loop streaming synthesis enables arbitrary-length LTX-2.3 video on a 16GB RTX 3080 — nazgut · 2026-08-26
- WAN 3.0 arrives on Lumen Pro: one-shot 30-second cinematic clips with dialogue — aziz4ai · 2026-08-26