AI Speed Box
Photoshop (Beta) New Feature: Select Body Parts
- AI Image
- Adobe Photoshop
2024/12/19
Available Now (Available)
Report: AIBRAHAM
Hunyuan Video by Tencent
- AI Video
- AI Sound
- Hunyuan
Tencent launched Hunyuan Video on 2024.12.03, a powerful open source video generation AI model.
https://aivideo.hunyuan.tencent.com
https://huggingface.co/tencent/HunyuanVideo/discussions
https://slashpage.com/mintbear/Hunyuan-01-intro
2024/12/03
Available Now (Available)
Hunyuan Video by Tencent
Category
- AI Video
- AI Sound
Gen
- Hunyuan
Date
2024/12/03
Summary 🍀🧸
Tencent launched Hunyuan Video on 2024.12.03, a powerful open source video generation AI model.
URL
https://aivideo.hunyuan.tencent.com
URL
https://huggingface.co/tencent/HunyuanVideo/discussions
URL
https://slashpage.com/mintbear/Hunyuan-01-intro
Release
Available Now (Available)
Hunyuan Video is an open source AI video model that converts text to video (T2V) released by Tencent in China on 2024.12.03.
Reference
Tencent Official
How to run HunyuanVideo on a single 24gb VRAM card
Etc
Tech
HunyuanVideo is a large-scale model for text-based video generation, adopting the “Dual-stream to Single-stream” hybrid model design to effectively process text and video data. 
1.
Dual-stream stage: Text and video tokens are processed independently through multiple Transformer blocks, allowing each modality to learn its own appropriate representation.
2.
Single-stream stage: Effective fusion of multimodal information is achieved by combining text and video tokens and feeding them to subsequent Transformer blocks.
