Alibaba open-sources Qwen-Image-2.1: 7B image model with native RGBA output, claimed to beat closed rivals
thione · x · 2026-09-28
Alibaba's Qwen team released Qwen-Image-2.1, an open-weight image generation and editing model whose visual generation component has just 7B parameters. The team claims it beats most closed models on their own benchmark (independent evals pending), and it runs on consumer GPUs like an RTX 3090.
Key capabilities:
- Native RGBA generation and editing: isolate objects or edit text on transparent layers
- Handles up to 10 reference images at once for group portraits, virtual try-ons, or room design
- Local edits guided by circles, masks, or painted marks
- Architecture changes and KV cache reuse speed up inference, especially with multiple reference images
Available on Hugging Face, GitHub, and Model Scope with a HF demo. The research license bars commercial use; business users must apply for a separate license.
More from Multimodal
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16
- Hand-editing 0.2% of weights plus 100 CPU-minutes turns an English TTS model into an 18MB Sanskrit one — kastnerkyle · 2026-11-16
- Zyphra open-sources textnorm tool, lifting TTS structured-data accuracy by up to 22 points — kastnerkyle · 2026-11-16
- Testing Qwen Image 2.1 and Minimax H3 on anime-to-photo conversion and film photo restoration — Ant_6431 · 2026-11-16
- Second take of a 'Cubee run' video generated with Minimax H3 — JahJedi · 2026-11-16
- Non-artist builds 14-chapter hand-painted storybook game with Fable 5.2 in 4 hours — jradoff · 2026-11-16