# Qwen releases Qwen-Image-2.1-Turbo on Hugging Face

> The 7B text‑to‑image model runs with an 8‑step schedule and works out of the box in Diffusers.

Oossa · 2026-10-09 · https://oossa.com/en/qwen-releases-qwen-image-2-1-turbo-on-hugging-face

Qwen has added Qwen-Image-2.1‑Turbo to Hugging Face. It is an accelerated checkpoint of the 7 billion‑parameter Qwen‑Image‑2.1 model for text‑to‑image generation and image editing. The model runs with a built‑in 8‑step denoising schedule, so users do not need to configure a sampler. It loads directly with the QwenImage21Pipeline in the Diffusers library and supports several aspect‑ratio presets up to 2048 × 2048 pixels.

## The facts

- Model size: 7 B parameters
- Release date: 2026‑10‑09

## Why it matters

Developers can generate high‑resolution images with fewer steps, cutting compute time for creative projects.

## Sources & references

1. [New model on Hugging Face: Qwen/Qwen-Image-2.1-Turbo (text-to-image)](https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo) – Qwen, 2026-10-09
2. [Alibaba Qwen Releases Qwen-Image-2.1-Turbo, an 8-Step 7B Image Model](https://www.marktechpost.com/2026/10/09/alibaba-qwen-releases-qwen-image-2-1-turbo-an-8-step-7b-image-model/) – MarkTechPost, 2026-10-09

Last updated: 2026-10-09