ComfyUI: nVidia TensorRT (Workflow Tutorial)

Показать описание

nVidia TensorRT is officially implemented for Comfy UI and Supports SD 1.5, SD 2.1, SDXL, SDXL Turbo, SD3, SVD, and SVD XT. Using ComfyUI, you gain 14% to 32% faster image generation in Stable Diffusion. I explain how TensorRT works for Stable Diffusion in Comfy and provide a comprehensive workflow tutorial to generate TensorRT .engine files.

------------------------

------------------------

TimeStamps:

0:00 Intro.
01:55 TensorRT in ComfyUI.
15:02 TensorRT Engine Workflow.
42:30 Build TensorRT Engine.
43:56 Workflow Integration.

Рекомендации по теме

Комментарии

TensorRT is more complicated than what I have covered. I have restricted the explain in relevancy to Comfy UI and Stable Diffusion. LoRA works, ControlNet support is not added yet. Hope the video is helpful.

controlaltai

Happy to be a member... Thank you for all your work!!

onebitterbit

I don't often leave comments but I had to for this video! I came in just wanting to learn about Tensor RT(which I did) but I also came out with a killer All-In-One workflow! Seriously, this is great, thank you!

fraz

I am always grateful for the best lectures. I may have missed something, but the explanation about Static batch size is missing.

moviecartoonworld

Error occurred when executing TensorRTLoader:

'NoneType' object has no attribute 'create_execution_context', only on SD3 workflow, when try to load the tensorrt... any suggestion? Thanks!!

onebitterbit

Does tensor rt work with animatediff already by any chance?

andrejlopuchov

Hello sir. Were you able to make it work with cosxl models?

ultimategolfarchives

can you generate a picture and upload it to a folder that we can download from? this would allow us to use the workflow easily without having to build it all manually.

takaikioshi

"ComfyUI TensorRT engines are not yet compatible with ControlNets or LoRAs. Compatibility will be enabled in a future update."
Not interesting for the moment

hleet

Turbo and sd3 are closed licensed. Wgaf about them except hobbyists? And sdxl lightning is open license but you ignored it. Very disappointing.

DoctorMandible

ComfyUI: nVidia TensorRT (Workflow Tutorial)

ComfyUI: nVidia TensorRT (Workflow Tutorial)

How to Run Stable-Diffusion using TensorRT and ComfyUI

Comfy UI with Tensor RT

Generate Images Faster with Stable Diffusion and RTX

ComfyUI Tutorial: Save the Strawberry People! Optimizing AI Image Generation with TensorRT Nodes

ComfyUI - SUPER FAST Images in 4 steps or 0.7 seconds! On ANY stable diffusion model or LoRA

1000% FASTER Stable Diffusion in ONE STEP!

How to install New StableSwarm Beta.

How to Train Your Own AI Model (LoRA) Using Personal or Favorite Celebrity Photos Without any GPU.

2X SPEED BOOST for SDUI | TensorRT/Stable Diffusion Full Guide | AUTOMATIC1111

Stable Diffusion Realistic AI Consistent Character (Instant Method Without Training)

Is Stable Diffusion WebUI Forge Just Plain Better Than A1111 WebUI?

Stable Diffusion 3 IS FINALLY HERE!

Stable diffusion up to 50% faster? I'll show you.

Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmUI SD Web UI that Utilizes ComfyUI

The NEW KING of Face Swappers! Reactor Tutorial. Roop is dead.

Double Your Stable Diffusion Inference Speed with RTX Acceleration TensorRT: A Comprehensive Guide

Stable Diffusion Increases Image Size 64 times, Plus new SDXL TensorRT Version Released

Install and use ComfyUI Stable diffusion (AMD or NVDA GPU, SDXL 1.0): Step-by-Step Guide 🚀

Stable Diffusion 10FPS Subsecond Speeds!

Comfyanonymous Resigns and starts new Company | Comfy UI

ControlNet - Openpose [TensorArt]

ControlNet - Openpose face [TensorArt]

Train Your Own LoRa Model Online (Website) with XL Support : A Complete Tutorial