Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Stable Videostability.ai · Low evidenceStable Video Diffusion is Stability AI's model for creating video content from text prompts using diffusion-based generation. It supports text-to-video generation with customizable frame rates (3–30 fps, including 14 and 25 fps) and delivers videos in about two minutes. It can be deployed on users' own infrastructure under a self-hosted license, aligning with Stability AI's open-source, creator- and enterprise-friendly approach.
Stability AIStable VideoParse Score