phineas-pta/comfy-trt-test
attempt to use TensorRT with ComfyUI
This project helps ComfyUI users speed up image generation by leveraging NVIDIA TensorRT. It takes your existing Stable Diffusion models as input and converts them into an optimized format for faster output on RTX 20xx-40xx GPUs. This is primarily for advanced users who want to accelerate their Stable Diffusion workflows in ComfyUI.
No commits in the last 6 months.
Use this if you have an NVIDIA RTX 20xx, 30xx, or 40xx GPU and want to significantly reduce the time it takes to generate images with Stable Diffusion models in ComfyUI.
Not ideal if you need features like ControlNet, IPAdapter, LoRA (currently limited), or Stable Video Diffusion, as these are not fully supported, or if you are not comfortable with manual installation and command-line operations.
Stars
80
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/phineas-pta/comfy-trt-test"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Comfy-Org/comfy-cli
Command Line Interface for Managing ComfyUI
YanWenKun/ComfyUI-Docker
🐳Dockerfile for 🎨ComfyUI. | 容器镜像与启动脚本
Comfy-Org/ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
runpod-workers/worker-comfyui
ComfyUI as a serverless API on RunPod
Acly/comfyui-tooling-nodes
Nodes for using ComfyUI as a backend for external tools. Send and receive images directly...