Testing Stable Diffusion Inference Performance with Latest NVIDIA Driver including TensorRT ONNX from rangabati ram sampath song Watch Video
Preview(s):
Gallery
Play Video: (Note: The default playback of the video is HD VERSION. If your browser is buffering the video slowly, please play the REGULAR MP4 VERSION or Open The Video below for better experience. Thank you!)
⏲ Duration: 10:56 👁 View: 15K times ✓ Published: 28-May-2024
Description: UNLOCK INSANE SPEED BOOSTS with NVIDIA's Latest Driver Update or not?Are you ready to turbocharge your AI performance? Watch me compare the brand-new NVIDIA 555 driver against the older 552 driver on an RTX 3090 TI for #StableDiffusion. Discover how TensorRT and ONNX models can skyrocket your speed! Don't miss out on these game-changing results!<br/><br/>1-Click fresh Automatic1111 SD Web UI Installer Script with TensorRT and more ⤵️<br/>https://www.patreon.com/posts/86307255<br/><br/>0:00 Introduction to the NVIDIA newest driver update performance boost claims<br/>0:25 What I am going to test and compare in this video<br/>1:11 How to install latest version of Automatic1111 Web UI<br/>1:40 The very best sampler of Automatic1111 for Stable Diffusion image generation / inference<br/>1:57 Automatic1111 SD Web UI default installation versions<br/>2:12 RTX 3090 TI image generation / inference speed for SDXL model with default Automatic1111 SD Web UI installation<br/>2:22 How to see your NVIDIA driver version and many more info with nvitop library<br/>2:40 Default installation speed for NVIDIA 551.23 driver<br/>2:53 How to update Automatic1111 SD Web UI to the latest Torch and xFormers<br/>3:05 Which CPU and RAM used to conduct these speed tests CPU-Z results<br/>3:54 nvitop status while generating an image with Stable Diffusion XL - SDLX on Automatic1111 Web UI<br/>4:10 The new generation speed after updating Torch (2.3.0) and xFormers (0.0.26) to the latest version<br/>4:20 How to install TensorRT extension on Automatic1111 SD Web UI<br/>5:28 How to generate a TensorRT ONNX model for huge speed up during image generation / inference<br/>6:39 How to enable SD Unet selection to be able to use TensorRT generated model<br/>7:13 TensorRT pros and cons<br/>7:38 TensorRT image generation / inference speed results<br/>8:09 How to download and install the latest NVIDIA driver properly and cleanly on Windows<br/>9:03 Repeating all the testing again on the newest NVIDIA driver (555.85)<br/>10:06 Comparison of other optimizations such as SDP attention or doggettx<br/>10.:35 Conclusion of the tutorial<br/><br/>NVIDIA's Latest Driver: Does It Really Deliver?<br/><br/>In this video, we dive deep into NVIDIA's newest driver update, comparing the performance of driver versions 552 and 555 on an RTX 3090 TI running Windows 10. We'll explore the claims of speed improvements, particularly with #ONNX runtime and TensorRT integration, using the popular Automatic1111 Web UI.<br/><br/>What You'll Learn:<br/><br/>Driver Comparison: Direct performance comparison between NVIDIA drivers 552 and 555.<br/>Setup and Installation: Step-by-step guide on setting up a fresh #Automatic1111 Web UI installation, including the latest versions of Torch and xFormers.<br/>ONNX and TensorRT Models: Detailed testing of default and TensorRT-generated models to measure speed differences.<br/>Hardware Specifications: Insights into the hardware used for testing, including CPU and memory configurations.<br/>Testing Procedure:<br/><br/>Initial Setup:<br/>
Play Video: (Note: The default playback of the video is HD VERSION. If your browser is buffering the video slowly, please play the REGULAR MP4 VERSION or Open The Video below for better experience. Thank you!)