LongCat-Image-Edit

It is the image editing variant of LongCat-Image, supporting bilingual (Chinese-English) editing tasks with state-of-the-art performance among open-source models. It excels in instruction-following capabilities and visual consistency while maintaining high image quality.

Key Features:

• Superior Precise Editing: Supports global editing, local editing, text modification, and reference-guided editing. The model demonstrates strong semantic understanding and precise execution of editing instructions.
• Consistency Preservation: Ensures non-edited regions retain attributes such as layout, texture, color tone, and subject identity unless explicitly altered by the instruction. This is particularly evident in multi-turn editing scenarios.
• Benchmark Performance: Achieves leading performance in image editing tasks with improved inference efficiency, outperforming other open-source models. 

---

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: 05.12.2025
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-Edit 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.