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
#120 / 159
ELO
857.0
Appearances
4,789
95% CI
-8/8
Image Editing
#59 / 76
ELO
928.0
Appearances
5,001
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.
Anima
wavespeed-ai/anima/text-to-imageA fast 2B anime image model for tag-driven illustrations, native 1K or 1.5K output, and prompt-guided variations from one uploaded image.
Anima LoRA
wavespeed-ai/anima/text-to-image-loraAnima with faithful support for up to three custom character or style LoRAs, plus native 1K or 1.5K generation and prompt-guided variations from one image.
BiRefNet V2
fal-ai/birefnet/v2Remove backgrounds with dedicated foreground segmentation, preserving transparent edges. Optionally return the mask itself.
GPT Image 2.5 Flare Edit
openai/gpt-image-2.5/flare/editGPT Image 2.5 Flare edits images from natural-language instructions with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.
GPT Image 2.5 Flare
openai/gpt-image-2.5/flare/text-to-imageGPT Image 2.5 Flare generates images from text prompts or edits images with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.