diff --git a/src/routes/generative-ai/+page.svelte b/src/routes/generative-ai/+page.svelte index beb6588e8b9a2..6092ea797a266 100644 --- a/src/routes/generative-ai/+page.svelte +++ b/src/routes/generative-ai/+page.svelte @@ -1,86 +1,261 @@ + - + - - - + + + - - + +
-

Stable Diffusion + ONNX Runtime

-

Use ONNX Runtime to accelerate this popular image generation model.

-

Benefits

-
-
-
-

Run Stable Diffusion outside of a Python environment

-
- Inference Stable Diffusion → +
+ Representing generative AI +
+ +

What is Generative AI?

+

+ Generative AI refers to a type of artificial intelligence that creates new content—such as + text, images, audio, or code—based on patterns learned from existing data. Unlike + traditional AI models, which primarily classify or predict based on given inputs, generative + AI models produce entirely new outputs. +

+ They accomplish this through advanced techniques like deep learning, often using models such + as Transformers and Generative Adversarial Networks (GANs). Examples include AI that generates + human-like text responses, creates realistic images from descriptions, or composes music. Generative + AI is driving innovation across industries by enabling personalized experiences, automating creative + processes, and opening new possibilities for content generation! +

+
+ +
+
+
+
+

Generative AI models

+ +
+
+
+
+

Text Generation Models

+

+ Text generation models are AI systems designed to generate human-like text based on + prompts. They're used in chatbots, content creation, summarization, and creative + writing. Check out our llama 3 and phi-3 demos below: +

+
+ +
+ Llama 3 + Phi-3 + Gemma + Mistral +
+
+ + + +
+
+

Other Models

+

+ Other generative models create diverse outputs like code, video, or 3D designs. These + models expand creative possibilities, enabling automation and innovation in fields + ranging from software development to digital art. +

+
+ Request a model on GitHub +
+
-
-
-

- Speed up inference of Stable Diffusion on NVIDIA and AMD GPUs +

+
+
+

ONNX Runtime Gen AI

+

+ Use ONNX Runtime Gen AI for its high performance, scalability, and flexibility in deploying + generative AI models. With support for diverse frameworks and hardware acceleration, it + ensures efficient, cost-effective model inference across various environments. +

+
+
+

+ Run ONNX Runtime - Generative AI on:

-
- Accelerate Stable Diffusion → +

+ {#key cycleIndex} + {cycleWords[cycleIndex]} + Desktop, mobile, and browser usage of ONNX Runtime Gen AI + {/key} +

+
+ +
+
+
+

Multiplatform

+

Whether it be Desktop, Mobile, or Browser, run ONNX Runtime on the platform of your choosing!

+
+
+
+
+

On Device

+

Run ORT GenAI locally, without privacy concerns and inference however you desire.

+
+
+
+
+

Multimodal compatibility

+

You aren't limited to just LLMs with ORT GenAI - you can use your favourite vision or (soon) omni models too.

+
+
+
+
+

Easy to use!

+

Getting ramped up is super easy! Get started using any of the various examples we have below!

+
+
-

Performance

-

The average latency in seconds on Stable Diffusion v1.5 and v2.1 models:

-
-
- Stable Diffusion v1.5 latency graphs -
+
+

Tutorials & Demos

+

+ Raring to go? Bring your models to all platforms and get started with any of the following + tutorials and demos: +

- Stable Diffusion v2.1 latency graphs +
+
+
+ A cappuccino used to inference with Phi3 vision +
+
+

Phi-3 Vision

+

+ A Desktop app demo to interact with text and images simultaneously. +

+
+ Try it out! +
+
+
+
+
+ UI of the vision LLM chat app +
+
+

LLM Chat App

+

+ An LLM chat app with UI. Pick your favourite model and get chatting! +

+
+ Try it out! +
+
+
+
+
+ Genny's model testing UI +
+
+

Genny (model tester)

+

A demo app to debug and test models with ORT GenAI.

+
+ Try it out! +
+
+
+
-

Large Language Models + ONNX Runtime

-

- ONNX Runtime supports many popular large language model (LLM) families in the Hugging Face Model - Hub. These, along with thousands of other models, are easily convertible to ONNX using the - Optimum API. -

-
diff --git a/src/routes/generative-ai/aibrain.webp b/src/routes/generative-ai/aibrain.webp new file mode 100644 index 0000000000000..03107b21fa52b Binary files /dev/null and b/src/routes/generative-ai/aibrain.webp differ diff --git a/src/routes/generative-ai/browser.png b/src/routes/generative-ai/browser.png new file mode 100644 index 0000000000000..cbb14360a30e8 Binary files /dev/null and b/src/routes/generative-ai/browser.png differ diff --git a/src/routes/generative-ai/coffee.png b/src/routes/generative-ai/coffee.png new file mode 100644 index 0000000000000..be588435b9c1e Binary files /dev/null and b/src/routes/generative-ai/coffee.png differ diff --git a/src/routes/generative-ai/desktop.png b/src/routes/generative-ai/desktop.png new file mode 100644 index 0000000000000..73fb99cc91b7f Binary files /dev/null and b/src/routes/generative-ai/desktop.png differ diff --git a/src/routes/generative-ai/genny.png b/src/routes/generative-ai/genny.png new file mode 100644 index 0000000000000..44256175aa2a3 Binary files /dev/null and b/src/routes/generative-ai/genny.png differ diff --git a/src/routes/generative-ai/mobile.png b/src/routes/generative-ai/mobile.png new file mode 100644 index 0000000000000..7f7cbd5d0347d Binary files /dev/null and b/src/routes/generative-ai/mobile.png differ diff --git a/src/routes/generative-ai/vision_UI.png b/src/routes/generative-ai/vision_UI.png new file mode 100644 index 0000000000000..93ed7cdbde6fb Binary files /dev/null and b/src/routes/generative-ai/vision_UI.png differ