Post Thumbnail

Stability AI introduces transformation of 2D photos into 3D scenes

Stability AI has announced the release of an innovative AI model called Stable Virtual Camera, capable of transforming two-dimensional images into immersive video materials with realistic depth and perspective. This technological achievement marks significant progress in the field of generative artificial intelligence and virtual cinematography.

Stable Virtual Camera represents a substantial development of the virtual camera concept, traditionally used in digital filmmaking and 3D animation. The integration of generative AI into this toolkit opens unprecedented possibilities for control and customization of created content.

The technical capabilities of the new model are impressive:

  • Generation of “new angles” of a scene based on one to 32 source images.
  • Creation of videos with dynamic camera movement trajectories.
  • Support for preset shooting modes: “Spiral”, “Dolly Zoom”, “Move”, and “Pan”.
  • Ability to work with various formats: square (1:1), portrait (9:16), and landscape (16:9).
  • Capability to generate video sequences up to 1000 frames long.

Despite the impressive capabilities, Stability warns about potential limitations of the current research version. The model may show quality degradation when working with images containing people, animals, or “dynamic textures” like water. “Highly ambitious scenes, complex camera trajectories crossing objects or surfaces, and irregularly shaped objects can cause a flickering effect, especially when target angles differ significantly from the source images,” the company notes in its blog.

This technological breakthrough comes during a difficult period for Stability AI. The company, known for its popular image generation model Stable Diffusion, attracted new investments last year from significant figures such as Eric Schmidt and Napster founder Sean Parker, who are seeking to restore the business. Earlier it was reported that Stability co-founder and former CEO Emad Mostaque led the company to financial problems, resulting in employee layoffs, the failure of a partnership with Canva, and growing investor concerns about the company’s prospects.

Autor: AIvengo
For 5 years I have been working with machine learning and artificial intelligence. And this field never ceases to amaze, inspire and interest me.
Latest News
XPeng introduced world's first female humanoid robot

Chinese electric car manufacturer XPeng introduced the new generation humanoid robot IRON. And this is the first female humanoid!

Michael Burry bet 1.1 billion dollars against Nvidia and Palantir

Michael Burry - this is a legendary investor who predicted the 2008 mortgage crisis. And now he's making a loud move again. Michael bet 1.1 billion dollars in put options against 2 major companies from the AI sector. These are Nvidia and Palantir.

Anthropic conducts interviews with models before sending to retirement

Anthropic published a policy for "decommissioning" outdated AI versions. Key commitment is to preserve weights of all public and actively used internal models for at least the company's lifetime. So that in the future access can be restored if necessary.

Nvidia head believes there is no AI bubble

Nvidia founder Jensen Huang dispelled concerns about a bubble in the AI market. And according to him, the company's latest chips are expected to bring 0.5 trillion dollars in revenue.

Sam Altman is tired of money questions

Sam Altman is tired of questions about OpenAI's money. And this became obvious during a joint interview with Satya Nadella on the Bg2 podcast.