Completed
17:07 Testing the Prompt on Nano Banana Pro: Quality Assessment
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
FLUX 2 vs FLUX SRPO - New FLUX Training Kohya SS GUI Premium App With Presets and Features
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Introduction to New FLUX Training Improvements and Local Training Showcase
- 2 0:24 Understanding FLUX SRPO Model: High Realism with Minimal VRAM Requirements
- 3 0:38 Updated Configurations for Training Realism on 6GB VRAM GPUs Locally
- 4 1:07 FLUX 2 Announcement and Setting Up Comparisons with BFL Playground
- 5 1:45 FLUX 2 Dev Model Technical Specs: 32 Billion Parameters and Hardware Challenges
- 6 2:11 Overview of Changes in SECourses Premium Kohya Trainer Version 35
- 7 2:46 Development Updates: GUI Improvements and Full Torch Compile Support
- 8 3:13 LoRA Presets Update: VRAM Optimization and Speed Improvements via Torch Compile
- 9 3:27 Introducing On-the-Fly FP8 Scaled LoRA Training Support
- 10 3:42 Quality Comparison Analysis: BF16 vs FP8 Scaled Weights LoRA
- 11 4:24 VRAM Usage and Speed Analysis: Block Swap Count Reduction with FP8 Scaled
- 12 5:12 Why 32GB GPUs Don't Need FP8 Scaled: Fitting Completely with Torch Compile
- 13 5:36 DreamBooth Training Specifics: BF16 Mixed Precision and Tab Selection
- 14 6:18 New 80GB GPU Configuration: Significant Training Speed Up and Cost Analysis
- 15 7:39 New Feature: FLUX FP8 Converter Tool for DreamBooth Models
- 16 8:10 Verifying Quality of Converted FP8 Scaled Models vs Original BF16
- 17 9:03 New Image Pre-processing Tool: Visualizing How Kohya Sees Your Dataset
- 18 9:34 Demonstration of Pre-processing: Identifying Padding and Orientation Issues
- 19 10:38 Additional Features: Memory Efficient Loading and CPU Text Encoder Caching
- 20 11:23 New Automated Model Downloader Tool: Installation and Model Selection Guide
- 21 12:35 FLUX 2 vs FLUX 1 Context: Can the New Model Replace Existing Workflows?
- 22 13:03 Setting Up the Generation Comparison: SRPO Fine-tune vs Base vs FLUX 2 Pro
- 23 14:13 Analyzing First Comparison Results: Portrait Quality and Realism Assessment
- 24 15:02 Second Comparison Test: Handling Unrealistic Elements and Animals in Prompts
- 25 15:33 Importance of Resolution and Platform Choice for FLUX 2 Quality
- 26 16:24 Analyzing Second Results: Prompt Adherence and Realism in FLUX 2 vs SRPO
- 27 17:07 Testing the Prompt on Nano Banana Pro: Quality Assessment
- 28 17:39 Comparison with Seedream 4 Model and Final Thoughts on FLUX 2 Potential
- 29 18:50 Current Recommendation: Why Qwen Image Realism is the Temporary King
