Generative Models

AnimateDiff is an open-source AI model that generates smooth animations from static images using advanced diffusion techniques.

Stable Video Diffusion enables the generation of short video clips from static images through advanced diffusion techniques.

Autoregressive model for video generation.

ControlNet is a sophisticated model designed for conditional image generation, enabling users to integrate additional control signals for enhanced visual outputs.

DreamBooth is an open-source AI model for personalized image generation and custom fine-tuning of diffusion models. Create unique subjects with high-quality synthesis.

DALL·E Mini is an open-source text-to-image Generative Adversarial Network that creatively synthesizes high-quality images from textual prompts.

StyleGAN2 is a state-of-the-art Generative Adversarial Network (GAN) designed for high-quality image synthesis, enabling researchers and developers to create photorealistic images with fine-grained control.