Launch Open Source Video with Wan 2.2 and Pruna AI
The release of Wan 2.2 has reignited interest in open source video within the community. This version marks a significant leap forward from 2.1, delivering sharper physics, faster generation, and greater control over the process. With its fully open-source nature, Wan 2.2 provides an opportunity to create high-quality videos at an accessible price.
In collaboration with Pruna AI, we have released our optimized version of Wan 2.2, allowing users to test videos at an astonishingly low cost of just 5 cents per video. This is even less than leading image generators on the AI market. With generation times around 30 seconds, Wan 2.2 becomes an excellent tool for rapidly testing video prompts without compromising on quality.
For users wanting to explore the capabilities of Wan 2.2, various options are available: fast image-to-video and text-to-video generation in resolutions of 480p and 720p, priced from 5 to 10 cents per video. Additionally, versions without optimizations are available at slightly higher prices, offering more features for video creation.
Working with the Wan 2.2 API is straightforward and accessible through the Replicate platform. Users can easily import the necessary libraries and start generating videos using text and image prompts. We plan to release more optimizations in collaboration with Pruna over the coming days, so stay tuned for updates and join our community.
Create Music with Lyria 3, Our Newest Generation Model
Explore the capabilities of Seedream 5.0 for image creation
Похожие статьи
Launching the Adaptive Learning Speculator System ATLAS
Together AI launches ATLAS, an adaptive learning speculator system for enhancing language models.
Z.ai Launches GLM-5V-Turbo: A New Multimodal Vision Coding Model
Z.ai has introduced GLM-5V-Turbo, a new vision coding model optimized for multimodal workflows.
Explore the Video Generation Capabilities of Veo 3.1
Discover the new video generation capabilities of Google's Veo 3.1.