Agentic AI Workflows Explained: Patterns, Infrastructure, and GPU Requirements
Agentic workflows plan, loop, and burst differently than a single model call — here's what that means for the infrastructure underneath.
All
Ever wanted to start generating your own unique creations using your own custom dreambooth model, but didn't have any idea where to start or what settings to choose? Well, one of our users decided to put together this epically comprehensive guide by running a ton of tests on Runpod! I'm hoping it will give you a good starting point, and maybe solve some of the common problems when getting started with dreambooth training. Enjoy!
Update: Here's how to fix some of the issues when running with the latest versions of dreambooth/automatic1111
Original Video:
Warning: it contains a TON of content
Here's the TOC
0:00 Introduction
0:49 Setup and Install
7:15 Starting experiments
15:49 How to add more disk space to your existing Runpod
17:08 xformers related bug error
18:20 How to resume a failed training
18:49 All tests have been completed time to check their training samples
25:36 Finding a good seed to compare all checkpoints within each trained model
48:30 How to download all decided best checkpoints via runpodctl
49:09 How to use web terminal when jupyter connection is not available
49:56 Where to put downloaded safetensors model files
51:05 Final Comparison
1:00:20 Conclusion
Related posts
Author profile: Zhen Lu
