Alibaba Qwen Releases Qwen-Image-2.1-Turbo: 7B Image Model in 8 Steps

Alibaba's Qwen team released Qwen-Image-2.1-Turbo, an accelerated checkpoint of its open-weight Qwen-Image-2.1 model that generates and edits images in 8 denoising steps instead of 40 on the same 7B architecture. It is available via Alibaba Cloud Model Studio at CNY 0.1 per image, but weights carry a research-only license.

• 8 denoising steps instead of 40 — 5x fewer on the same 7B architecture
• Qwen3-VL 8B text encoder, 2K output and native RGBA transparency
• API costs CNY 0.1 per image, 2.5x cheaper than Pro
• Research license only: commercial self-hosting needs permission