Qwen Releases Wan2.2, a 5B Open-Source Video Model
The new Apache 2.0 licensed model from Alibaba's team generates video from either text prompts or still images, offering a unified approach in a compact package.
Alibaba's Qwen team has released Wan2.2-TI2V-5B, a new open-source model for video generation. At five billion parameters, the model offers a relatively compact solution for creating short video clips and is available under the permissive Apache 2.0 license, allowing for commercial use.
A key feature of Wan2.2-TI2V-5B is its unified architecture for handling multiple input types. It can generate video from a text description (text-to-video) or animate a still image based on a prompt (image-to-video). This flexibility is packaged for broad accessibility, with the official release available in the popular Diffusers format.
A Versatile Tool for Generative Video
The release adds another strong contender to the rapidly evolving open-source video landscape. Its 5B parameter size strikes a balance between capability and accessibility, potentially enabling more developers and researchers to experiment with high-quality video generation without requiring massive computational resources.
The model's dual-input nature and commercial-friendly license position it as a versatile foundation for building creative applications. Developers can access the weights and usage examples for Wan2.2-TI2V-5B on the Hugging Face Hub.
Sources
- Visit
Wan-AI/Wan2.2-TI2V-5B-Diffusers
Hugging Face
0 comments
No comments yet. Be the first to weigh in.
More in Text → Video
JD.com Enters Open-Source AI Video with JoyAI-Echo
The Chinese e-commerce giant has released a new model capable of generating long-form, multi-shot videos with synchronized audio from text prompts.
Baidu Releases NAVA for Text-to-Video with Audio
The new model from the Chinese tech giant uses a Multimodal Diffusion Transformer to generate synchronized audio and video from text or image prompts.
NVIDIA Releases SANA, a Camera-Controllable Video Model
The new model, SANA-WM, uses a bidirectional diffusion process to give creators fine-grained control over camera movement and video editing.