# NVIDIA/Stable-Diffusion-WebUI-TensorRT

TensorRT Extension for Stable Diffusion Web UI

Repository: https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT
Canonical: https://ross.abutalabs.com/products/stable-diffusion-webui-tensorrt
Language: Python
License: MIT
License Family: permissive
Last push: 2024-06-14T06:05:57+00:00

## Health v2 (maintenance only)
Score: 18/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 75
- inputs: {"age_days": 1058, "days_push": 810, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1989, forks 164 (observed 2026-08-28T04:06:02.980634+00:00)

## What it is
An NVIDIA extension for the Stable Diffusion Web UI (Automatic1111) that accelerates image generation using TensorRT-optimized engines on RTX GPUs. It supports SD 1.5, 2.1, SDXL, SDXL Turbo, and LCM, including LoRA conversion to TensorRT format.

## Use cases
- speed up stable diffusion image generation on nvidia rtx gpus
- generate tensorrt engines for sdxl
- use lora checkpoints with tensorrt acceleration
- optimize stable diffusion webui performance
- run stable diffusion faster with lower latency

## When to choose
- you use Automatic1111 Web UI with an NVIDIA RTX GPU and want maximum generation speed
- you need optimized engines for specific resolutions and batch sizes
- you want to accelerate SDXL or SD 1.5/2.1 inference with TensorRT

## When to avoid
- you don't have a compatible NVIDIA RTX GPU
- you use a different UI like ComfyUI or InvokeAI
- you frequently change resolutions and can't afford building dynamic engines or extra VRAM usage

## Facets
- artifact type: plugin
- maturity: active
- function: image-processing, llm-inference, gpu-computing
- domain: image-processing, gpu-computing, artificial-intelligence
- platform: windows, python
- tags: stable-diffusion, tensorrt, automatic1111, nvidia, image-generation, webui-extension, linux, gpu

## Member repositories
- NVIDIA/Stable-Diffusion-WebUI-TensorRT (main) score 18

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:02.980634+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:02:47.190224+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT (fetched 2026-08-28T04:06:02.980634+00:00, sha a2050ab86b97)
- Data as of 2026-08-30T08:39:29.467469+00:00.