LongCat-Image

It is an open-source, bilingual (Chinese-English) foundation model designed for text-to-image generation. It addresses key challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility. With only 6 billion parameters, it outperforms larger open-source models across benchmarks, showcasing efficient architecture design.

Key Features:

• Efficiency & Performance: Achieves superior performance with 6B parameters, surpassing models several times its size.
• Chinese Text Rendering: Demonstrates high accuracy and stability for common Chinese characters, with industry-leading coverage of the Chinese dictionary.
• Photorealism: Enhanced through innovative data strategies and training frameworks, producing highly realistic images.

---

The model is a component of the image generation pipeline, consisting of:

• Text encoder: ~8.3B parameters,
• Transformer: ~6.2B parameters,
• VAE: ~83M parameters,

Total: ~14.6B parameters

Announce Date: 04.12.2025
Parameters: 6B
Developer: Meituan-longcat
Diffusers Version: 0.30.0.dev0
vLLM-Omni Version: 0.12.0rc1
License: Apache 2.0

Use our pre-built public endpoints for free to test inference and explore LongCat-Image capabilities. You can obtain an API access token on the token management page after registration and verification.

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

• maximize endpoint performance,
• enable full context for long sequences,
• ensure top-tier security for data processing in an isolated, dedicated environment,
• use custom weights, such as fine-tuned models or LoRA adapters.

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.