Latte

Latent diffusion transformer for video generation with spatial-temporal attention.

Open SourceSelf HostedOffline CapableGPU Required (16GB+ VRAM)
0.0 (0)

About

Latte is a latent diffusion transformer for video generation that factorizes spatial and temporal modeling into dedicated attention blocks, reaching competitive quality with efficient training. The repository provides PyTorch model definitions, pretrained weights, and training, sampling, and evaluation code from the paper. Developed by Monash University and Shanghai AI Lab. Released under the Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
License
Apache-2.0
Minimum VRAM
16 GB
Added
Apr 3, 2026

Related Tools

Featured

Open-source video generation model by Tencent with text and image conditioning.

Open SourceSelf HostedOfflineGPU 24GB+
Advanced
0.0 (0)

Image-to-video generation model by Alibaba DAMO Academy.

Open SourceSelf HostedOfflineGPU 12GB+
Advanced
0.0 (0)

Updated CogVideo model by Zhipu AI with improved video quality.

Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)

Infinite-length music-driven video generation with visual conditioning.

Open SourceSelf HostedOfflineGPU 12GB+
Advanced
0.0 (0)

Text-to-video generation framework with cascaded latent diffusion.

Open SourceSelf HostedOfflineGPU 16GB+
Advanced
0.0 (0)

Open-source text-to-video model by Zhipu AI/Tsinghua with 2B and 5B variants.

Open SourceSelf HostedOfflineGPU 12GB+
Advanced
0.0 (0)
Browse all Video Generation tools