

ControlVideo | Free AI tool
Training-free Controllable Text-to-Video Generation
Introduction
ControlVideo
Official PyTorch implementation of “ControlVideo: Training-free Controllable Text-to-Video Generation”
ControlVideo adapts ControlNet to the video counterpart without any finetuning, aiming to directly inherit its high-quality and consistent generation
Citation
If you make use of our work, please cite our paper.
@article{zhang2023controlvideo,
title={ControlVideo: Training-free Controllable Text-to-Video Generation},
author={Zhang, Yabo and Wei, Yuxiang and Jiang, Dongsheng and Zhang, Xiaopeng and Zuo, Wangmeng and Tian, Qi},
journal={arXiv preprint arXiv:2305.13077},
year={2023}
}
Acknowledgement
This work repository borrows heavily from Diffusers, ControlNet, Tune-A-Video, and RIFE.
There are also many interesting works on video generation: Tune-A-Video, Text2Video-Zero, Follow-Your-Pose, Control-A-Video, et al.
Recommendation
DeepSeek
DeepSeek offers self-developed models including DeepSeek R1, DeepSeek Chat V3, and DeepSeek Coder. As a Chinese AI company focused on AGI, it has developed a next-generation conversational AI that enhances search, programming, and creative tasks with versatile intelligent interaction.
ChatGPT
Supports GPT-4, GPT-4o and GPT-3.5. OpenAI's next-generation conversational AI, using intelligent Q&A capabilities to solve your tough questions.
Google Gemini 2.0
Gemini, a groundbreaking AI model series developed by Google, contains Gemini 1.5 Flash, Gemini 1.5 Pro and Gemini Pro, seamlessly operates across various modalities including text, images and code.
xAI Grok-3
Grok-3 is the third-generation AI model in the Grok series, designed to enhance understanding, problem-solving, and contextual awareness.