WaveSpeed.ai
首頁/探索/wavespeed-ai/longcat-image/text-to-image
text-to-image

text-to-image

LongCat-Image

wavespeed-ai/longcat-image/text-to-image

LongCat-Image is a 6B parameter bilingual (Chinese-English) text-to-image model from Meituan, excelling at multilingual text rendering, photorealism, and deployment efficiency. Ready-to-use REST inference API with best performance and no cold starts.

Input
width
height
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

A creative movie poster design. In the center is a futuristic robot cat. The title text "LongCat AI" is written in large, bold, metallic letters at the top. High contrast, 8k resolution.

您的請求將花費 $0.15 每次運行。

使用 $10 您可以運行此模型大約 66 次。

還有一件事：:

示例查看全部

A creative movie poster design. In the center is a futuristic robot cat. The title text "LongCat AI" is written in large, bold, metallic letters at the top. High contrast, 8k resolution.
A rainy cyberpunk street at night, a bright neon sign hanging on the wall that says "Open 24 Hours" and "便利店". Cinematic lighting, realistic reflections on the wet ground.
Professional food photography of a delicious beef burger with melted cheese, fresh lettuce, and tomatoes. Steam rising, water droplets on the vegetables, shallow depth of field, studio lighting
A hyper-realistic close-up portrait of an old fisherman with a white beard, wearing a yellow raincoat. detailed skin texture, weather-beaten face, dramatic lighting, sharp focus on eyes.
A panoramic view of a ruined modern metropolis reclaimed by nature. Skyscrapers are collapsing and covered in massive green vines and waterfalls. A rusted aircraft carrier sits in the middle of a flooded street. Sunset lighting, melancholic atmosphere, highly detailed textures, movie concept art.

README

LongCat-Image — Text-to-Image

LongCat-Image is an open-source, bilingual (Chinese-English) foundation model for image generation developed by Meituan. With only 6B parameters, it addresses key challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility.

Where LongCat-Image fits best

  • Chinese and English text rendering in images
  • Photorealistic image generation
  • High-volume generation with efficient resource usage
  • Marketing and product visuals with text overlays

Key Features

• Exceptional Efficiency and Performance

With only 6B parameters, LongCat-Image outperforms larger open-source models across multiple benchmarks, demonstrating efficient model design.

• Powerful Chinese Text Rendering

Superior accuracy in rendering Chinese characters with industry-leading Chinese dictionary coverage. More stable than existing SOTA open-source models.

• Remarkable Photorealism

Innovative data strategy and training framework delivers high-quality, photorealistic image generation.

• Bilingual Support

Natively supports both Chinese and English prompts with excellent text rendering in both languages.

• Resource-conscious

The efficient 6B parameter architecture keeps GPU usage moderate, ideal for batch jobs and cost-sensitive pipelines.

Related Models on WaveSpeedAI

  • LongCat-Image Edit – Image editing with the same bilingual text rendering capabilities.

More Image Tools on WaveSpeedAI

  • Nano Banana Pro – Google's Gemini-based text-to-image model for sharp, coherent, prompt-faithful visuals.
  • Seedream V4 – ByteDance's style-consistent, multi-image generator ideal for posters and campaigns.
  • Qwen Edit Plus – An enhanced Qwen-based image editor for precise inpainting and local style changes.