LongCat-Video Technical Report

Papers with Code Trending Papers
video-generation diffusion-transformer text-to-video image-to-video video-continuation open-source 10b-parameters

Summary

LongCat-Video is a 13.6B parameter video generation model based on Diffusion Transformer, supporting text-to-video, image-to-video, and video-continuation tasks with efficient long video generation using coarse-to-fine and block sparse attention.

Video generation is a critical pathway toward world models, with efficient long video inference as a key capability. Toward this end, we introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across multiple video generation tasks. It particularly excels in efficient and high-quality long video generation, representing our first step toward world models. Key features include: Unified architecture for multiple tasks: Built on the Diffusion Transformer (DiT) framework, LongCat-Video supports Text-to-Video, Image-to-Video, and Video-Continuation tasks with a single model; Long video generation: Pretraining on Video-Continuation tasks enables LongCat-Video to maintain high quality and temporal coherence in the generation of minutes-long videos; Efficient inference: LongCat-Video generates 720p, 30fps videos within minutes by employing a coarse-to-fine generation strategy along both the temporal and spatial axes. Block Sparse Attention further enhances efficiency, particularly at high resolutions; Strong performance with multi-reward RLHF: Multi-reward RLHF training enables LongCat-Video to achieve performance on par with the latest closed-source and leading open-source models. Code and model weights are publicly available to accelerate progress in the field.
Original Article
View Cached Full Text

Cached at: 05/23/26, 12:22 AM

Paper page - LongCat-Video Technical Report

Source: https://huggingface.co/papers/2510.22200 Published on Oct 25, 2025

·

Submitted byhttps://huggingface.co/taesiri

taesirion Oct 28, 2025

Authors:

,

,

,

,

,

,

,

,

,

Abstract

LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.

Video generation is a critical pathway toward world models, with efficient long video inference as a key capability. Toward this end, we introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across multiple video generation tasks. It particularly excels in efficient and high-quality long video generation, representing our first step toward world models. Key features include: Unified architecture for multiple tasks: Built on theDiffusion Transformer(DiT) framework, LongCat-Video supportsText-to-Video,Image-to-Video, andVideo-Continuationtasks with a single model; Long video generation: Pretraining onVideo-Continuationtasks enables LongCat-Video to maintain high quality andtemporal coherencein the generation of minutes-long videos; Efficient inference: LongCat-Video generates 720p, 30fps videos within minutes by employing acoarse-to-fine generationstrategy along both the temporal and spatial axes.Block Sparse Attentionfurther enhances efficiency, particularly at high resolutions; Strong performance withmulti-reward RLHF: Multi-reward RLHF training enables LongCat-Video to achieve performance on par with the latest closed-source and leading open-source models. Code and model weights are publicly available to accelerate progress in the field.

View arXiv pageView PDFGitHub2.6kAdd to collection

Get this paper in your agent:

hf papers read 2510\.22200

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper11

#### meituan-longcat/LongCat-Video Text-to-Video• UpdatedOct 29, 2025 • 1.29k • 478 #### Nishant2414/LongCat-Video Text-to-Video• Updated16 days ago • 15 • 1 #### fjkane/LongCat-Video-bf16 Text-to-Video• UpdatedDec 19, 2025 • 1 #### Alfikun/LongCat-Video Text-to-Video• UpdatedFeb 22 • 1 Browse 11 models citing this paper## Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2510.22200 in a dataset README.md to link it from this page.

Spaces citing this paper211

Browse 211 spaces citing this paper## Collections including this paper6

Browse 6 collections that include this paper

Similar Articles

Long Video Generation (4 minute read)

TLDR AI

The article introduces A²RD, a novel architecture for generating consistent long videos using agentic autoregressive diffusion. It proposes a Retrieve–Synthesize–Refine–Update cycle and a new benchmark, LVBench-C, to address semantic drift in long-horizon video synthesis.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Papers with Code Trending

VideoChat3 is a fully open, efficient, and generalist video-centric multimodal large language model that introduces Inflated 3D Vision Transformer (I3D-ViT) and Adaptive Frame Resolution for streaming video perception, along with scalable video data synthesis pipelines, achieving superior performance with only 4B parameters.

meituan-longcat/LongCat-2.0

Hugging Face Models Trending

LongCat-2.0 is a large-scale MoE language model with 1.6 trillion total parameters and ~48B activated per token, trained on AI ASIC superpods with 1M-context data. It achieves strong performance on coding and agentic tasks.