Wan2.1-T2V-1.3B is a compact open-weight text-to-video diffusion model. It converts text prompts into short video sequences and is distributed in Diffusers format on Hugging Face. The model can be run locally with PyTorch or through cloud inference providers, making high-quality video generation accessible to developers.
In the Text to video space, Wan2.1 T2V 1.3B takes a focused approach. It focuses on generating short videos from natural language descriptions without access to proprietary video generation services. Wan2.1 T2V 1.3B is an open-source project aimed at AI developers and content creators. Wan2.1 T2V 1.3B is open source under the Apache-2.0 license. Wan2.1 T2V 1.3B is available on the command line and API.
Wan-AI builds and maintains Wan2.1 T2V 1.3B, and it first shipped in 2025. The project is developed in the open on GitHub with 16.6k stars. Among its 3 catalogued features are Text-to-Video Generation, Diffusers Pipeline, and High Efficiency. It exposes integrations via a public API.
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