Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

SVD-XT

Model basics

Reasoning traces

Not supported

Context length

2K tokens

Max output length

No data

Model type

视觉大模型

Release date

2023-11-21

Model file size

9.56GB

MoE architecture

Total params / Active params

10.0B / N/A

Knowledge cutoff

No data

Inference modes

No mode data

SVD-XT

Open source & experience

Code license

MIT License

Weights license

开源不可商用- 不可以商用

GitHub repo

https://github.com/Stability-AI/generative-models

Hugging Face

https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt

Live demo

No live demo

SVD-XT

Official resources

Paper

Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

DataLearnerAI blog

No blog post yet

SVD-XT

API details

API speed

No data

No public API pricing yet.

SVD-XT

Benchmark Results

No benchmark data to show.

SVD-XT

Publisher

Stability AI

View publisher details

Stable Video Diffusion - XT

Model Overview

更多介绍参考： https://www.datalearner.com/blog/1051700786899649

SVD模型简介

SVD全称Stable Video Diffusion，是StabilityAI最新的开源文本生成视频大模型。这个模型是基于Stable Diffusion 2.1进行初始化，然后通过在图像模型中插入时空卷积和注意力层来构建这个视频生成模型的架构，最终在1.52以视频数据集上训练得到。

SVD-XT可以生成20帧的576x1024分辨率的视频，而SVD只能生成14帧。

SVD模型的详细信息： https://www.datalearner.com/ai-models/pretrained-models/SVD

下图是样例结果：

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送