qwen-qwen-image-2-1-turbo

What is qwen-qwen-image-2-1-turbo

This is a Hugging Face Space image generation and processing demo application based on Qwen2.1-VL-Turbo.

Key features

• Supports text-to-image generation; create images simply by entering a description
• Supports multi-image editing; upload up to 10 images and reference them with <image_1> etc.
• Natively supports transparency output; RGBA images can be requested in the prompt
• Optional prompt enhancement that optimises input descriptions via the official rewriter
• Uses an 8-step distilled checkpoint and AOTInductor compilation to accelerate inference

Who it is for

Suitable for researchers, developers and non-commercial demo users who need fast text-to-image generation or multi-image editing.

How to get started

1. Visit https://huggingface.co/spaces/hugging-apps/qwen-qwen-image-2-1-turbo
2. For text-to-image generation, clear the input gallery and enter a descriptive prompt
3. For image editing, upload up to 10 images and reference them in the prompt with <image_1> etc.
4. Optionally tick Enhance prompt to optimise the prompt

Compiled from public descriptions on the tool's official website / README / launch page. Pricing and user numbers have not been verified; please check the official website. Some sections were drafted with AI assistance. Written in Chinese and English; other languages are machine-translated.