Model Mondays S1:E4 - Hands-on With Visual Generative AI

Join us for Model Mondays – a weekly show where we round up all the latest AI model news and put one model in the spotlight for a deeper dive.

In this episode, we’re joined by Ken Hoge as we dive into the world of visual generative AI and learn to work with text-to-image and image-to-image capabilities for content creation . We’ll get hands-on with the Stability AI models and learn how to craft suitable prompts to get diverse, representative, and high-quality image generation on Azure AI Foundry.

Session Resources:
https://aka.ms/model-mondays
https://aka.ms/model-mondays/discord
https://aka.ms/model-mondays/chat

Explore The Models
https://aka.ms/model-mondays/collection

Watch The Replay
https://developer.microsoft.com/en-us/reactor/events/25355/

Transcript

1. New Series · Starts Mar 10 https://aka.ms/model-mondays Model Mondays 10:30 am PT | 1:30 pm ET
2. Senior AI Advocate https://aka.ms/model-mondays/RSVP Nitya Narasimhan, PhD Sharmila Chockalingam Senior Product Marketing Mgr. Mar 31, 2025 – 10:30am PT | 1:30pm ET Welcome to Model Mondays
3. Sharmila Chockalingam 5 Key Things To Know This Week! Model Mondays Highlights
4. ❶ · Try Model Context Protocol (MCP) in Azure https://aka.ms/model-mondays MCP In Azure AI Foundry Reduce Development Complexity and Enhance productivity with Azure AI Agent Service and MCP compatible clients.
5. ❷ · Try Anthropic Models https://aka.ms/model-mondays Anthropic SOTA models on Azure Databricks Azure customers can now use the Claude "think" tool optimized with business data and guide Claude to effciently perform complex tasks.
6. ❸ · Try Responses API https://aka.ms/model-mondays Responses API A powerful API enabling AI application to retrieve information, process data and take action seamlessly
7. ❹ · Try Computer-Using Agent (CUA) https://aka.ms/model-mondays Computer-Using Agent (CUA) A breakthrough AI model that navigates software interfaces, executes tasks and automates workflows
8. ❺ · Try Images Playground https://aka.ms/model-mondays Images Playground Generate images from text prompts using AI models like Stability, Dall-E and Bria AI
9. Hands-on with Visual Generative Models What is Visual Generative AI? How can I use text-to-image and image-to-image capabilities with Stable Diffusion? Ken Hoge Global Partnership Lead, Stability AI
10. ❶· What is Stable Diffusion? kenneth.hoge@stability.ai Stability AI suite of state-of-the- art image models on Azure AI Foundry Diverse Outputs: Creates images representative of the world, not just one type of person, with different skin tones and features, without the need for extensive prompting. Stable Diffusion 3.5 Large represents one of the most advanced image models available today. It delivers unmatched text-to-image generation with key capabilities such as: Versatile Styles: Capable of generating a wide range of styles and aesthetics like 3D, photography, painting, line art, and virtually any visual style imaginable. Prompt Adherence: Our analysis shows that SD3.5 Large leads the market in prompt adherence, allowing the model to closely follow a given text prompt, making it a top choice for efficient, high-quality performance.
11. kenneth.hoge@stability.ai ❷· What can I create with it? E-Commerce Product Assets, Virtual Try-on Marketing & Advertising Creative Design & Creative Tools Ad Platforms Post-Production/VFX Our use cases span multiple industries and applications for image generation, while also expanding into new and emerging areas. Models designed to meet various business needs Stable Diffusion 3.5 Large: prompt adherence, style variety, diverse outputs Stable Image Ultra: photorealism Stable Image Core: speed and efficiency
12. kenneth.hoge@stability.ai ❸· What are some examples? Simple implementation ideas can generate instant growth Builders and entrepreneurs are experimenting with Stable Diffusion in Azure AI Foundry every day Leading e-commerce platforms are using Stable Diffusion models to quickly transform their businesses. By placing offered products in realistic settings, sellers have increased ad impressions by +45% and increased click through rates by +25%. How Stable Diffusion is Revolutionizing Marketing INPUT OUTPUT
13. kenneth.hoge@stability.ai ❹· How can I get started? Stability AI engineer Sanwal: How to get started with image generation Azure AI Foundry engineer Jessica: How to upload your own source image for image-to-image capabilities To get started: 1. Navigate to Azure AI Foundry. 2. Search for Stability AI in the model catalog. 3. Once you have navigated to the Stability AI catalog page, chose the model you wish to begin experimenting with.
14. Hands-on with Fine-Tuning Models Rashaud Savage Product Manager (AI Core), Microsoft What is Fine-Tuning and why do we need it? How can we fine-tune Mistral models? What are the pros & cons here?
15. Join the #model-mondays channel https://aka.ms/model-Mondays/chat Q&A Office hours every Friday on Discord – bring questions, share your projects!
16. Watch the Livestream Join the Conversation Explore the Resources Mon 1:30pm ET Microsoft Reactor https://aka.ms/model-mondays/RSVP Fri 1:30pm ET Azure AI Discord https://aka.ms/model-mondays/Discord Watch or Star GitHub Repo https://aka.ms/model-monday #ModelMondays