RTX 5090 vs RTX 3090 Ti Performance Comparison for AI Image Generation Models
Software Engineering Courses - SE Courses via YouTube
Gain a Splash of New Skills - Coursera+ Annual Just ₹7,999
Introduction to Programming with Python
Overview
Syllabus
0:00 Introduction to the video and PC configuration and specs
0:30 Backends of ComfyUI and the GPUs and machine config
0:40 Testing FLUX DEV model performance on RTX 5090 and RTX 3090 Ti
0:53 RTX 5090 and RTX 3090 Ti GPU sensor values while generating images on FLUX Dev
2:10 How to change precision to 8-bit FP8 vs 16-bit on SwarmUI including FP16 T5 XXL
3:34 Testing FLUX Fill inpainting and outpainting model performance on RTX 5090 and RTX 3090 Ti
4:56 Testing speed impact of changing prompt when generating new images
6:23 Testing Stable Diffusion 3.5 Medium SD 3.5 Medium model performance on RTX 5090 and RTX 3090 Ti
8:27 Testing Stable Diffusion 3.5 Large SD 3.5 Large model performance on RTX 5090 and RTX 3090 Ti
9:02 Where you can learn more about the GPU and the machine that is being used for benchmarking
9:42 What kind of Overclocking I am doing on RTX 5090, overlocking levels
10:12 Testing Stable Diffusion XL SDXL model performance on RTX 5090 and RTX 3090 Ti
11:41 Testing Stable Diffusion 1.5 SD 1.5 model performance on RTX 5090 and RTX 3090 Ti
12:54 Comparison table and evaluation of the models and the speeds of RTX 5090 and RTX 3090 Ti
15:30 How to install SwarmUI and make it working with RTX 5000 series GPUs and how to download AI models ultra fast
17:01 How to use our unified SwarmUI model downloader to download FLUX, SD 1.5, SDXL, SD 3.5 models and more models
19:00 How to upgrade Torch / ComfyUI backend to make it work on RTX 5000 series GPUs
19:58 Which folder will be deleted and replaced with pre-made backend
Taught by
Software Engineering Courses - SE Courses