Stable Diffusion
Open Source by Stability AI
Latent diffusion model that generates images from text prompts. Released with open weights, allowing local and third-party deployment.
Generative AIComputer VisionCreative AI
Made by Speech Graphics
Offline audio-driven facial animation software that generates lip sync and expressions for cinematics and cutscenes from a speech recording.
Open Source by Stability AI
Latent diffusion model that generates images from text prompts. Released with open weights, allowing local and third-party deployment.
Platform by Synthesia
AI video generation platform that creates videos with digital avatars and synthetic voiceovers from text, used for training and corporate communications.