Gradio demo of CharacterGen (SIGGRAPH 2024)
text-to-3D & image-to-3D
Convert images to 3D models
Create a dynamic torus knot scene with random properties
Text-to-3D and Image-to-3D Generation
Transform ideas into AR experiences with a 3D model
Play interactive 3D Pyramids game
Create interactive 3D scenes with torus knots
Create a dynamic and colorful 3D scene with random objects and lights
Transform images into 3D depth models
Create a dynamic 3D scene with random shapes and lights
Generate a 3D model and video from images
Generate 3D models from text prompts
CharacterGen is an AI-powered tool that enables the generation of 3D characters from single images. Presented as a Gradio demo at SIGGRAPH 2024, it offers a user-friendly interface for creating detailed 3D models, making it a valuable resource for artists, animators, and game developers.
• 3D Character Generation: Create realistic 3D characters from 2D image inputs.
• Customization Options: Adjust settings to refine character features and details.
• Real-Time Rendering: Generate and preview characters in real time.
• Cross-Industry Applications: Suitable for gaming, animation, VR, and more.
What types of images work best with CharacterGen?
• High-resolution, clear images with a single subject work best. Faces or full-body shots can be used depending on the desired output.
Can I use CharacterGen for commercial projects?
• Yes, CharacterGen is designed to support both personal and professional use cases, including commercial projects like game development or animation.
What formats are the generated characters exported in?
• Characters are typically exported in standard 3D model formats such as OBJ, STL, or FBX, ensuring compatibility with most 3D modeling software.