Completed
9:15 Using Sage Attention vs. xFormers for Optimal Performance
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
ComfyUI and SwarmUI Installation on RunPod with RTX 5000 Series GPUs - Complete Setup Guide
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Introduction to ComfyUI & SwarmUI Installation on RunPod
- 2 0:22 Advanced Features of the One-Click Installer Sage Attention, xFormers, Blackwell
- 3 1:03 Demonstration on RTX Pro 6000 GPU & VRAM Optimization
- 4 1:52 Introducing the High-Speed Unified Model Downloader
- 5 2:06 Starting the Tutorial: Downloading & Preparing the Installer Files
- 6 2:45 Registering and Setting Up Your RunPod Account & Billing
- 7 3:04 Selecting the Optimal RunPod GPU RTX Pro 6000 and Server
- 8 3:54 Critical Step: Configuring the RunPod Pod Template PyTorch 2.2.0
- 9 4:20 Setting Volume Disk, Container Disk, and Exposing HTTP Ports
- 10 5:09 Deploying the Pod and Accessing the Jupyter Lab Interface
- 11 5:46 Uploading and Extracting the ComfyUI Installer on RunPod
- 12 6:16 Running the ComfyUI Installation Command in the Terminal
- 13 7:22 How to Start ComfyUI with Custom Launch Arguments e.g., --gpu-only
- 14 8:13 Overview of Included Libraries Manager, Flash Attention, DeepSpeed, Triton
- 15 9:15 Using Sage Attention vs. xFormers for Optimal Performance
- 16 9:42 Connecting to the Live ComfyUI Web Interface
- 17 10:27 Introducing the Unified Model Downloader for ComfyUI & SwarmUI
- 18 11:01 Running the Model Downloader and Configuring the Download Path
- 19 11:43 Downloading FLUX Models for a ComfyUI Image Generation Test
- 20 13:22 Configuring the ComfyUI Workflow with Newly Downloaded FLUX Models
- 21 15:01 First Image Generation Test: Analyzing the Incredible Speed
- 22 15:53 Terminating ComfyUI and Preparing for SwarmUI Installation
- 23 16:25 Installing SwarmUI and Setting it Up via the Cloudflared Link
- 24 16:50 How to Configure SwarmUI to Use ComfyUI as a Self-Starting Backend
- 25 17:50 Downloading Wan 2.1 Video Generation Models with the Downloader
- 26 19:22 Importing Presets and Setting up a Wan 2.1 Video Generation in SwarmUI
- 27 20:21 First Video Generation Test with Wan 2.1 GGUF Version
- 28 21:26 Analyzing GGUF Performance and Deciding to Test the FP16 Model
- 29 22:54 Downloading the FP16 Wan 2.1 Model for a Performance Comparison
- 30 24:01 Installing Extra Features like RIFE Frame Interpolation
- 31 24:41 Re-configuring SwarmUI to Use the FP16 Model with 16-bit Precision
- 32 25:52 Analyzing FP16 Performance and VRAM Usage 57GB
- 33 26:28 Final Experiment: Using the Official Wan 2.1 Preset for Best Results
- 34 27:28 Final Results, Conclusion, and How to Get Further Help
