Wan
github.com
- Free plan
- Linux
- Self-hosted
What Wan is
Wan is a free, open-source suite of video foundation models that runs on Linux and can be self-hosted. It supports text-to-video, image-to-video, video editing, text-to-image, and video-to-audio tasks, including Chinese and English text inside generated videos. VACE accepts a prompt with optional video, mask, and image inputs for generation or editing. Wan-VAE encodes and decodes 1080P videos of any length while preserving temporal information. The T2V-14B model supports 480P and 720P output; T2V-1.3B supports 480P, while its 720P results are described as less stable. T2V-1.3B requires 8.19 GB of VRAM. The project reports about four minutes for a five-second 480P video on an RTX 4090 without quantization. Model downloads are offered through Hugging Face and ModelScope. Installation covers pip and Poetry, with PyTorch 2.4.0 or later required. Diffusers and ComfyUI integrations are listed, along with a local Gradio interface.
Who it suits
Wan suits developers and creators who can run Linux software locally or self-host it. Commercial use is permitted under the Apache-2.0 license.
Good to know, and what to watch
- Supports text-to-video and image-to-video
- Includes video editing and audio tasks
- Commercial use permitted
- Diffusers and ComfyUI integrations
- Local Gradio interface provided
- Requires Linux or self-hosting setup
- T2V-1.3B needs 8.19 GB VRAM
- 1.3B 720P output is less stable
- PyTorch 2.4.0 or later required
The verdict
Wan provides a broad, locally runnable model suite with multiple generation and editing workflows. Hardware and installation requirements matter, especially for higher-resolution output.
What the maker publishes
- Commercial use
- Yes source
- Downloads
- Model weights are linked for download through Hugging Face and ModelScope. source
- Generation tasks
- The models support text-to-video, image-to-video, video editing, text-to-image, and video-to-audio tasks. source
- GPU requirement
- The T2V-1.3B model requires 8.19 GB VRAM according to the repository, which also reports about four minutes to generate a five-second 480P video on an RTX 4090 without quantization. source
- Hardware requirement
- The T2V-1.3B model requires 8.19 GB of VRAM, and the project says it can generate a five-second 480P video on an RTX 4090 in about four minutes without quantization. source
- Image and video tasks
- The repository lists image-to-video, video editing, text-to-image, and video-to-audio among its supported tasks. source
- Image-to-video
- Yes source
- Installation
- The installation guide documents pip and Poetry installation methods. source
- Integrations
- The project says Wan2.1 T2V and I2V were integrated into Diffusers and that Wan2.1 was integrated into ComfyUI. source
- License
- The repository identifies its license as Apache-2.0. source
- Local interface
- The repository includes instructions for running a local Gradio interface. source
- Maximum resolution
- 720p source
- Maximum video length
- 0.083333 source
- Model downloads
- The project provides model downloads through Hugging Face and ModelScope. source
- Product
- Wan2.1 is an open suite of video foundation models for video generation. source
- Prompt extension
- Prompt extension can use the DashScope API or a local Qwen model. source
- Requirements
- The quickstart says to ensure PyTorch 2.4.0 or later before installing dependencies. source
- Resolutions
- The repository lists T2V-14B at 480P and 720P, and T2V-1.3B at 480P; it cautions that 1.3B results at 720P are less stable than at 480P. source
- Resolution support
- The T2V-14B model supports 480P and 720P, while T2V-1.3B supports 480P. source
- Runtime
- The quickstart instructs users to install dependencies with PyTorch 2.4.0 or later and provides command-line and local Gradio inference examples. source
- Support
- The repository directs users to Discord and WeChat groups to contact the research or product teams. source
- Text generation
- Wan2.1 can generate Chinese and English text within videos. source
- Text-to-video
- Yes source
- Text to video
- Wan2.1 supports text-to-video generation with 1.3B and 14B models. source
Checked against the maker's pages on 8 Oct 2026.