Stability AI has released a new AI model, Stable Virtual Camera, that the company claims can transform 2D images into “immersive” videos with realistic depth and perspective.
Virtual cameras are tools often used in digital filmmaking and 3D animation to capture and navigate scenes in real time. With Stable Virtual Camera, Stability sought to add generative AI to the mix to deliver greater control and customizability, the company said in a blog post.
Stable Virtual Camera generates “novel views” of a scene from one or more images (up to 32 total) at camera angles that a user specifies. The model can generate videos that travel along “dynamic” camera paths or presets, including “Spiral,” “Dolly Zoom,” “Move,” and “Pan.”
The current version of Stable Virtual Camera, a research preview, can generate videos in square (1:1), portrait (9:16), and landscape (16:9) aspect ratios up to 1,000 frames in length. Stability warns the model may produce lower-quality results in certain scenarios, however, particularly with images featuring humans, animals, or “dynamic textures” like water.
“Highly ambiguous scenes, complex camera paths that intersect objects or surfaces, and irregularly-shaped objects can cause flickering artifacts,” Stability notes in its blog post, “especially when target viewpoints differ significantly from the input images.”
Stable Virtual Camera is available for research use under a noncommercial license. It can be downloaded from the AI dev platform Hugging Face.
Stability, the beleaguered firm behind the popular image-generation model Stable Diffusion, raised new cash last year as investors including Eric Schmidt and Napster founder Sean Parker sought to turn the business around. Emad Mostaque, Stability’s co-founder and ex-CEO, reportedly mismanaged Stability into financial ruin, leading staff to resign, a partnership with Canva to fall through, and investors to grow concerned about the company’s prospects.
In the last few months, Stability has hired a new CEO, appointed “Titanic” director James Cameron to its board of directors, and released several new image-generation models. Earlier in March, the company teamed up with chipmaker Arm to bring an AI model that can generate audio, including sound effects to mobile devices running Arm chips.