Completed
7:30 Testing Nano-Banana first to see if we even need to fine-tune
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Fine-Tuned Qwen-Image-Edit vs Nano-Banana - Generating 1.2 Million Images
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Using Qwen-Image-Edit to generate 1.2 million images and cutting inference costs
- 2 5:45 The Task: Generating tables and workbenches in different colors
- 3 7:30 Testing Nano-Banana first to see if we even need to fine-tune
- 4 13:30 The Pricing Dilemma
- 5 16:26 Question: How did we evaluate the generated table quality
- 6 17:15 Question: How did we pass in the colors we wanted
- 7 18:48 How we kicked off the fine-tuning from the dataset
- 8 21:31 How Baseten provisions the GPUs to kick off a training job
- 9 24:44 What you see while fine-tuning
- 10 26:22 The inference optimizations
- 11 37:10 Using a Lighting LoRA speed up inference by reducing inference steps
- 12 39:26 General Questions
