Xingliu AI
Officially listedLiblibAI's one-stop AI image generation platform, with a library of 100,000+ LoRA styles.
Xingliu AI
Xingliu AI is a one-stop AI image generation platform from LiblibAI. Built on the in-house Star-3 large model, it is the official Chinese version of the globally popular design agent Lovart, with deep localization for Chinese users and a library of 100,000+ LoRA style models.
Core Capabilities
- Image Generation: Based on the Star-3 model, with fine image detail and zero AI look, supporting HD upscaling and smart image expansion
- Inpainting: Precisely modify parts of an image, fixing common AI problems such as hands
- Style Library: 100,000+ LoRA style models, with 200+ high-aesthetic styles added daily
- Multimodal Creation: One-stop generation of images, videos, 3D models, and audio
- Infinite Canvas: A professional editing environment with natural language interaction
Use Cases E-commerce product images, marketing materials, illustration, and short video assets. Especially suited to designers, e-commerce sellers, and content creators who need Chinese-language support and localized service.
Unique Advantages Compared with overseas products like Midjourney, Xingliu AI offers native Chinese semantic optimization and a Chinese-aesthetic style library, and its 100,000+ LoRA model library is industry-leading in scale — an ideal choice for users in China.
Editor's Recommendation Rated 4.3 on the App Store, with users generally praising its fast generation speed and good quality. Star-3 output approaches photorealistic quality, and the daily free allowance of 150 credits is enough to experience the core features.
Pricing
### 💰 定价模式：免费增值 **起步价**：免费 #### 主要方案 - **免费版**：每天150点数，可生成图片或简单编辑 - **付费会员**：购买额外算力点或订阅高级服务 #### 试用/其他信息 付费会员可获得生成内容的商用授权，生成的图片、视频可直接用于广告、电商等商业场景。
FAQ
Is Xingliu AI free?
Xingliu AI uses a freemium model: free users get 150 credits per day for generating images or simple edits. For more computing power or a commercial license, you can purchase a paid membership.
What are Xingliu AI's main features?
Core features include image generation based on the Star-3 model, a library of 100,000+ LoRA style models, inpainting, smart image expansion, video generation, 3D model generation, audio synthesis, and infinite canvas editing.
How does Xingliu AI differ from Midjourney?
Xingliu AI has a library of 100,000+ LoRA styles (Midjourney has only 3-4 base models), native Chinese semantic optimization, richer editing features, and more competitive pricing — an ideal choice for users in China.
Can images generated by Xingliu AI be used commercially?
Images generated by free users cannot be used commercially. Paid members receive a commercial license for generated content, and generated images and videos can be used directly in advertising, e-commerce, and other commercial scenarios.
Is Xingliu AI suitable for e-commerce sellers?
Very much so. Xingliu AI is optimized for e-commerce scenarios, supporting product image generation and marketing material creation, and paid members get a commercial license for direct use in store operations.
What are the characteristics of Xingliu AI's Star-3 model?
Star-3 is LiblibAI's in-house general-purpose image generation large model, with fine image detail and zero AI look. Recommended settings are CFG 3.5, 30-40 steps, and the Euler sampler; it suits illustration, photography, 3D, and many other styles.