Generative AI
Learn about integrating the power of generative AI in your apps and services. Use state-of-the-art models for text generation, audio synthesis, and more to create innovative experiences.
What is Generative AI?
Generative AI refers to artificial intelligence that creates new content—such as text, images, audio, or code—based on patterns learned from existing data. Generative AI leverages transformer models for text and diffusion models for images. These innovations are transforming industries, enabling personalized experiences, automating creative processes, and opening new possibilities for content generation!
Generative AI Models
Text Generation Models
Generate human-like text for chatbots, content creation, summarization, and more.
Image Generation Models
Create artwork or realistic images from descriptions using AI models like Stable Diffusion.
Audio Models
Generate audio, music, or speech from data inputs with AI models like Whisper.
Other Models
Generate diverse outputs like code, video, or 3D designs.
ONNX Runtime ❤️ Generative AI
Use ONNX Runtime for high performance, scalability, and flexibility when deploying generative AI models. With support for diverse frameworks and hardware acceleration, ONNX Runtime ensures efficient, cost-effective model inference across platforms.
Run ONNX Runtime on:
Desktop 
Multiplatform
Run ONNX Runtime on Desktop 🖥️, Mobile 📱, Browser 💻, or Cloud ☁️.
On Device
Inference privately 🔐 and save costs ⚙️ with on-device models.
Multimodal Compatibility
Use ONNX Runtime with vision or omni models. We work to quickly enable all new model scenarios 🚀.
Easy to Use
Get started quickly ⏩ with our examples and tutorials.
Tutorials & Demos
Get started with any of these tutorials and demos:
Olive Examples
Use Olive, a hardware-aware optimizer, to quickly generate the ideal ONNX model for your needs.
Try it out!