Stability AI, a developer of Stable Diffusion text-to-image AI, has introduced Stable Video Diffusion, an AI model creating videos from images, available for specific purposes under a research preview with limitations on text control and rendering clarity.
The models, SVD and SVD-XT, generate short, high-quality clips but have constraints like the inability to control by text or consistently render faces.
Despite its limitations, Stability plans to expand these models and introduce a text-based prompting tool, aiming for commercial applications in areas like advertising and education. However, financial issues have impacted the company's operations, including delayed payments and threats of service suspension from AWS.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.