Longcat Distilled

• 🏢 Meituan's LongCat team built this open video model
• 🆕 Distilled image-to-video variant for faster, fewer-step inference
• 🎬 Animates a still image into coherent motion
• 📏 Designed for long-duration video generation
• 🧠 Diffusion Transformer base architecture
• ⚡ Distillation sampling trades steps for speed
• 🎯 Emphasizes subject coherence and temporal stability
• 🔒 Weights released under the permissive MIT license

Meituan

Meituan is a Chinese technology company founded in 2010 by Wang Xing and headquartered in Beijing. Best known for its massive local services platform — spanning on-demand food delivery, consumer reviews, hotel bookings, and instant retail — Meituan listed on…

Longcat Distilled (image-to-video) is part of Meituan's LongCat-Video family, an open-source video generation effort from the company better known for food delivery and local services. LongCat-Video uses a Diffusion Transformer (DiT) architecture and unifies text-to-video, image-to-video, and video-continuation tasks in a single model, distinguishing tasks by the number of conditional frames supplied. The family is positioned for long-duration video generation.

This entry is the distilled image-to-video configuration: it takes a still reference image and animates it into video. Per Meituan's model card, the distilled setup uses fewer sampling steps for faster inference. That positions it against its same-family sibling Longcat Full Quality, which runs the full-step pipeline for maximum fidelity, while the Longcat Distilled and Longcat Full Quality siblings cover the prompt-to-video path.

According to Meituan's model card, the approach emphasizes cross-frame consistency, subject coherence, and temporal stability across long sequences.

The weights ship under the MIT License, allowing broad commercial and research use, though the license grants no rights to Meituan trademarks or patents.