Stable Video 3D

Stability AI licenses offer flexibility for your generative AI needs by combining our range of state-of-the-art open models with self-hosting benefits. SV3D takes a single object image as input and output novel multi-views of that object. We can then use those novel-views and SV3D to generate 3D meshes. SV3D comes in two variants tailored for different needs. SV3D_u focuses on generating orbital videos from single image inputs without camera conditioning, making it ideal for straightforward 3D visualizations. On the other hand, SV3D_p extends this capability to include both single images and orbital views, allowing for more complex 3D video creation along specified camera paths. SV3D is available for commercial use with a Stability AI Membership, offering a wide range of applications in various industries. For non-commercial purposes, model weights can be downloaded from the Hugging Face platform, accompanied by our comprehensive research paper.

How to Use

To use Stability AI models like SV3D, you can either obtain a commercial license through a Stability AI Membership or download model weights for non-commercial use from platforms like Hugging Face. Follow the usage instructions provided in the GitHub repository and technical reports for in-depth understanding.

Stability AI License's

Key Features

• Flexible licensing options for generative AI models
• Self-hosting benefits
• Access to state-of-the-art open models like SV3D
• Commercial and non-commercial use options
• Novel view synthesis and 3D generation from single images (SV3D)
• Two SV3D variants (SV3D_u and SV3D_p) for different needs

Use Cases

• Commercial applications across various industries (with Stability AI Membership)
• Non-commercial and academic projects (using model weights from Hugging Face)
• Generating orbital videos from single images (SV3D_u)
• Creating complex 3D videos along specified camera paths (SV3D_p)
• 3D visualizations
• 3D modeling