---
title: Data-Juicer-T2V-v2
canonical_url: "https://www.modelscope.cn/models/Data-Juicer/Data-Juicer-T2V-v2"
md_url: "https://www.modelscope.cn/models/Data-Juicer/Data-Juicer-T2V-v2.md"
repository: Data-Juicer/Data-Juicer-T2V-v2
last_updated: 2024-09-23
license: cc-by-4.0
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
library_name:
  - pytorch
frameworks:
  - Pytorch
language:
  - en
downloads: 66
stars: 3
tags:
  - text-to-video
---

# Data-Juicer-T2V-v2

> Data-Juicer-T2V-v2 - Data-Juicer 在 ModelScope 开源的模型。Data-Juicer (DJ, 228k). Through the Data-Juicer sandbox laboratory, we improved video generation training data and models, achieving the first place in the VBench leaderboard (2024.09.24) based on…

Data-Juicer/Data-Juicer-T2V-v2 是 ModelScope 魔搭社区上的text-to-video-synthesis模型，采用 cc-by-4.0 许可。

- **Repository**: Data-Juicer/Data-Juicer-T2V-v2
- **License**: cc-by-4.0
- **Tasks**: text-to-video-synthesis
- **Tags**: text-to-video
- **Downloads**: 66
- **Stars**: 3
- **Last updated**: 2024-09-23

Source: https://www.modelscope.cn/models/Data-Juicer/Data-Juicer-T2V-v2

---

# <span style="font-family: 'Courier New', monospace; font-weight: bold">Data-Juicer Sandbox: A Comprehensive Suite for Multimodal Data-Model Co-development

## Project description

The emergence of large-scale multi-modal generative models has drastically advanced artificial intelligence, introducing unprecedented levels of performance and functionality. 
However, optimizing these models remains challenging due to historically isolated paths of model-centric and data-centric developments, leading to suboptimal outcomes and inefficient resource utilization. 
In response, we present a novel sandbox suite tailored for integrated data-model co-development. This sandbox provides a comprehensive experimental platform, enabling rapid iteration and insight-driven refinement of both data and models. 
Our proposed "Probe-Analyze-Refine" workflow, validated through applications on [T2V-Turbo](https://github.com/Ji4chenLi/t2v-turbo) and achieve a new state-of-the-art on [VBench leaderboard](https://huggingface.co/spaces/Vchitect/VBench_Leaderboard) with 1.52% improvement from T2V-Turbo based on our previous state-of-the-art model [Data-Juicer (T2V, 147k)](https://modelscope.cn/models/Data-Juicer/Data-Juicer-T2V). Our experiment code and dataset are released at [Data-Juicer Sandbox](https://github.com/modelscope/data-juicer/blob/main/docs/Sandbox.md).


## Model description 🚀

This repository includes the `unet_lora.pt` file, which can transform [VideoCrafter2](https://ailab-cvc.github.io/videocrafter2/) into our <span style="font-family: 'Courier New', monospace; font-weight: bold">Data-Juicer-T2V</span>. Please refer to the code in [T2V-Turbo](https://github.com/Ji4chenLi/t2v-turbo) to utilize our model effectively.


## Guidelines on Inappropriate and Prohibited Use 🚫
This model is intended solely for research and educational purposes.

- Generating content that could be considered insulting or detrimental to individuals or their surroundings, including their culture, religion, etc., is strictly forbidden.
- The creation of content that is pornographic, violent, or graphically disturbing is not allowed.
- Users must not use the model to produce incorrect or misleading information.