Wan2.1
Wan2.1 is a comprehensive set of video basic models that support a variety of tasks, from text to video, from image to video, from video editing and from text to image. The 1.3B parameterized version can run on consumer-grade video cards with a requirement of 8.19 GB VRAM. The model has the ability to create Chinese and English texts in visual content and can perform video encoding and decoding operations with the Wan-VAE component up to 1080P resolution.
Wan2.1
69Wan-Video · Local AI / Self-Hosted LLM
Common commercial products in this category: ChatGPT, Claude, Gemini
- You can create video clips from text descriptions or existing images.
- You can perform video editing and audio production over video.
- You can produce visual content with Chinese and English text in video format.
- ↑ PositiveHacker News
Alibaba Open Source Large-Scale Video Generative Models: Wan2.1
“HF: Github: Wan2.1, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. Wan2.1 offers these key features: - SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial…”
- • NeutralGitHub Issue
RuntimeError: FlashAttention only supports Ampere GPUs or newer
“please support old gpus i have 4 2080ti 22Gb, but can not run this model”