LongCat-Image is a 6B parameter bilingual (Chinese-English) text-to-image model from Meituan. Excels at multilingual text rendering, photorealism, and deployment efficiency. Features powerful Chinese text rendering with industry-leading dictionary coverage.
Added Dec 6, 2025
Approx. Price
$0.034 per image
Model Type
text-to-image
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
Supported
Reference/edit images accepted • Route max 30 MB
Output Sizes
Number of Images
Default
1
Resolution
Default
1024*1024
Options (5)
1024*1024 (Square (1024x1024)), 1280*720 (Landscape (1280x720)), 720*1280 (Portrait (720x1280)), 1536*1024 (Wide (1536x1024)) +1 more
Seed
Default
-1
Control reproducibility (-1 for random).
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#125 / 165
ELO
859.0
Appearances
3,722
95% CI
-8/8
Image Editing
#62 / 79
ELO
938.0
Appearances
3,952
95% CI
-8/8
Release Date 2025-12 · Matched as LongCat Image
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare Longcat Image with similar models from the same provider or model family.
Longcat Image Edit
longcat-image-editLongCat-Image Edit is a 6B parameter bilingual (Chinese-English) image editing model from Meituan. Designed for bilingual image editing with exceptional text rendering capabilities. Edit Chinese and English text in images with photorealistic modifications.
Qwen Image 2.1 Edit
wavespeed-ai/qwen-image-2.1/editEdit from up to ten reference images with natural-language instructions, strong subject preservation, flexible framing, and native output up to 2K.
Qwen Image 2.1 Edit LoRA
wavespeed-ai/qwen-image-2.1/edit-loraEdit from up to ten references while applying up to three custom LoRAs for precise identity, product, or style control at up to 2K.
Qwen Image 2.1
wavespeed-ai/qwen-image-2.1/text-to-imageCreate high-quality images with strong prompt following, multilingual text rendering, flexible framing, and native output up to 2K.
Qwen Image 2.1 LoRA
wavespeed-ai/qwen-image-2.1/text-to-image-loraGenerate Qwen Image 2.1 artwork with up to three custom character, product, or style LoRAs and native output up to 2K.
Bria Product Holding
bria/product-holdingPlace one to three referenced products naturally into a person's hands while preserving the subject and scene. Built for e-commerce, lifestyle advertising, influencer content, and product campaigns.