Qwen-Image-2.1-Turbo

Model release Hugging Face 模型 · Qwen Source language: Chinese

官方机构模型仓库创建于 2026-10-09。仓库创建时间不等于正式发布日期。任务类型:text-to-image

Full text

🤖 ModelScope      🤗 HuggingFace      💻 GitHub      📑 Qwen-Image-2.1 Blog      🫨 Discord      💬 WeChat

Introduction

Qwen-Image-2.1-Turbo is an accelerated checkpoint of Qwen-Image-2.1 for text-to-image generation and image editing with 8 denoising steps. It uses the same 7B visual generation architecture and loads directly with QwenImage21Pipeline in Diffusers.

The checkpoint includes its recommended sampling schedule, so it is ready to use without manually configuring the scheduler. Generation uses CFG=1 by default, and prefix KV caching reuses the text and reference-image context across denoising steps.

For more details, see the GitHub repo and Qwen-Image-2.1 blog.

Quick Start

Installation

Install a CUDA-compatible PyTorch build, then install the latest Diffusers source and the following dependencies:

This checkpoint requires Diffusers with support for pipeline-configured sampling sigmas, added in PR #14950.

Text-to-Image

Load the checkpoint from Hugging Face:

The pipeline automatically uses the checkpoint's saved 8-step schedule. The text-to-image example uses 1696 × 2528 portrait resolution; the editing example uses 2048 × 2048.

Image Editing

Reuse the pipeline above to turn a yacht sketch into a photorealistic image:

Sampling

The recommended 8-step sampling schedule is saved with the checkpoint and loaded automatically. Setting num_inference_steps alone does not override it. For experiments, an explicit call-time sigmas argument overrides the saved schedule; other schedules have not been evaluated for this checkpoint.

Supported Aspect Ratios

Use the same resolution presets as Qwen-Image-2.1:

Showcase

Examples from the 8-step outputs in our Turbo showcase. Each category features one example.

Portrait Photography

Human Poses and Motion

Transparent Image Generation

Typography and Poster Design

UI and Information Layout

Single-Image Transformation

Input

Output

Multi-Reference Composition

Input

Output

Four-Image Interior Composition

Input

Output

License

This model is licensed under the Qwen Research License Agreement.

Feedback

Having issues with Qwen-Image-2.1-Turbo? Our official feedback form connects you directly with the Qwen Image research team. Share your prompts, images, or workflows to help us investigate and improve.

Submit Feedback →

Sources

← Back to the daily brief