Data Science & AI #28 - Next-Level Image Generation and composable prompts
Details
This event will focus on generative AI and image generation: how to use this technology for complex, real-world workflows.
A big thank you to Inovex for hosting this event with us! inovex is an innovation- and quality-driven IT project center with around 500 IT experts specializing in digital transformation. The company provides comprehensive support to businesses in digitalizing and agilizing their core operations and implementing new digital use cases. Thanks for sponsoring the location and food, we are looking forward to a great evening with you! They are located in Erlangen, Allee am Röthelheimpark 11.
We will have exciting talks and our usual chitchat with drinks. This is your opportunity to meet other data science professionals from the Nuremberg area, sharpen your skills and exchange ideas with like-minded professionals.
🗓️ Agenda
- 17:30 – Doors open, welcome
- 18:00 – Talk: Beyond DALL-E: Advanced Image Generation Workflows with ComfyUI
- 19:00- Talk: Composable, reusable prompts with familiar.
- 19:30 – Networking with food and drinks
Beyond DALL-E: Advanced Image Generation Workflows with ComfyUI (René Fa - Data Engineer @ inovex)
Image generation using AI has made huge progress over the last years, and many people still think that DALL-E with a text prompt is the best way to generate images.
There are well-known models like Stable Diffusion and Flux, which can be used with easy-to-use frontends like A1111 or Invoke AI, but if you want to do more complex or bleeding-edge workflows, you need something else.
In this talk, I want to show you ComfyUI, an open-source node-based GUI written in Python where you can build complex pipelines that are otherwise only possible using plain code.
Veit Heller: familiar - Summoning friendly AI sprites
LLMs are great at generating code, but they’re unreliable collaborators. Across projects, you end up re-typing the same constraints (“keep diffs small”, “don’t add deps”, “run tests”, “don’t leak secrets”, “don’t commit for me”), forget half of them, and still get different behavior every time.
familiar is a small CLI that turns prompts into composable, reusable building blocks: conjurings (how the agent should behave) and invocations (repeatable workflows). Prompts become versioned, linted, and shareable — and therefore more dependable.
In this short talk, I’ll show how familiar composes system instructions and task prompts, how linting keeps prompt libraries manageable, and how plugins let you swap agents without rewriting your workflow.
---
Join us for an evening of insightful talks, engaging discussions, and networking with fellow data science and AI enthusiasts.
We look forward to seeing you there!