Alibaba open-sources Qwen-Image-2.1: unified 7B gen+edit model with transparency and 10-image input
千问大模型 · wechat · 2026-09-20
The Qwen team open-sourced Qwen-Image-2.1, a 7B unified text-to-image and editing model (32-layer Single-Stream DiT). Highlights: mixed-granularity attention with KVCache reuse for efficient inference; native transparent-image generation and editing including RGBA subject extraction from photos; up to 10 reference images with circle/brush/mask-based local editing and stronger portrait/product consistency; improved text rendering and realism. Weights are on Hugging Face, ModelScope and GitHub.
More from Models
- Musk cites unsustainable Grok Bot costs as Hermes offers one-command agent migration — Teknium · 2026-11-04
- Hobbyist rewrites Qwen 0.6B weights with 39.8M tokens, no gradients, in 3h12m — Altruistic_Heat_9531 · 2026-11-04
- Same leak, reshared: ChatGPT's five family plan prices spotted again — heyshrutimishra · 2026-11-04
- KOL visits StepFun's Shanghai office, hints a powerful new model is coming — teortaxesTex · 2026-11-04
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- ByteDance open-sources Axion 1.0-35B agent foundation model with full reproducible recipe — pmttyji · 2026-11-04