Wan2.2-T2V-A14B is a large-scale text-to-video generation model with 14 billion parameters. It uses a diffusion-based approach and is distributed in a format compatible with the Hugging Face Diffusers library. The model supports detailed prompt-based video synthesis and includes computational efficiency optimizations for different GPU configurations.
In the Text to video space, Wan2.2 T2V A14B takes a focused approach. It focuses on generating high-quality videos directly from text prompts using diffusion techniques. Wan2.2 T2V A14B is an open-source project aimed at AI researchers, video creators, and developers. The project is open source (Apache-2.0). It ships for the command line and API.
Wan-AI builds and maintains Wan2.2 T2V A14B, and it first shipped in 2025. Development happens publicly on GitHub with 16.8k stars. Key capabilities include text-to-video, high-resolution video, and diffusers pipeline.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do