Alibaba's open-weight Qwen-Image-2.1 claims to beat closed models with 7B params
The Decoder · rss · 2026-09-21
Alibaba's Qwen team released Qwen-Image-2.1, an open-weight image generation model with just 7 billion parameters that reportedly beats closed models.
- Runs generation and editing on high-end consumer GPUs
- Supports transparency and up to ten reference images at once
- Research license bars commercial use; a separate Qwen license is required for commercial deployment
More from Multimodal
- AI art community share: underrated AI artists and OG Tezos crypto-artists to follow — Merzmensch · 2026-09-21
- Fix lands for MiniMax H3 VAE grid artifacts in ComfyUI via PR #16422 — marres · 2026-09-21
- The 'turn your pet into a paper box' image-gen prompt is sweeping X — AIandDesign · 2026-09-21
- Quantized Qwen Image 2.1 and Krea 2 Turbo hit 12s/9s 1MP renders on a 4070 Super — Ant_6431 · 2026-09-21
- Qwen-Image 2.1 repo reveals the official prompt format for best text-to-image results — mantafloppy · 2026-09-21
- Full AI Music Video Built with Suno, Wan 3 and Kling 3 — CactusMonkey12 · 2026-09-21