Tian Yu X John: Discussing Practical Gen AI Tips for Image Prompting
6Speaker Profile:
Tianyu is a generative AI practitioner, speaker, author. He founded a company dedicated to upskilling professionals in generative AI. He also chairs the GenAI Risk Chapter at RIMAS. With over 1,000 hours dedicated to generative AI tools, Tianyu has generated over 30,000 images and 10,000 videos. He holds a best-selling DALL-E course and recently published the book "Will ChatGPT Take My Job: Winning Strategies for Managers" in both English and Japanese.
Book Link: https://www.amazon.com/Will-ChatGPT-Take-Job-Strategies-ebook/dp/B0D6Y8ZX5Y
DALL-E course: https://www.udemy.com/course/the-dall-e-master-course/
Upcoming Video Generation Course in Singapore (Thursday 24 Oct 2024 4pm): https://lu.ma/p0g5ksm9
Description:
In this session Tian Yu talks about how to better prompt AI image tools like DALL-E 3 or Leonardo. He also discusses how to use images to generate videos, as a primer for his upcoming video generation course.
~~~
Technical Details:
Stable Diffusion: https://arxiv.org/abs/2112.10752
ControlNet: https://arxiv.org/abs/2302.05543
Segment Anything Model 2: https://ai.meta.com/sam2/
~~~
0:00 John Introduction
0:46 Tian Yu Introduction
5:05 Difference between prompting text models and image models
12:45 Difficulty of generating more than one character
18:51 ControlNet
28:30 DALL-E 3 Full Playbook
58:17 Leonardo Prompting
1:08:48 Painting Style Reference
1:18:50 Image to Video
1:25:48 Conclusion
~~~
AI and ML enthusiast. Likes to think about the essences behind breakthroughs of AI and explain it in a simple and relatable way. Also, I am an avid game creator.
Discord: https://discord.gg/bzp87AHJy5
LinkedIn: https://www.linkedin.com/in/chong-min-tan-94652288/
Online AI blog: https://delvingintotech.wordpress.com/
Twitter: https://twitter.com/johntanchongmin
Try out my games here: https://simmer.io/@chongmin