stabilityai / stable-diffusion-3.5-large-tensorrt

Stable Diffusion 3.5 Large TensorRT

Introduction

This repository hosts the TensorRT version of Stable Diffusion 3.5 Large created in collaboration with NVIDIA . The optimized versions give substantial improvements in speed and efficiency.

Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Model Details

Model Description

This repository holds the ONNX exports of the CLIP, T5, MMDiT and VAE models in BF16 precision. It also holds the MMDiT model in FP8 precision. The transformer model was quantized to FP8 precision using NVIDIA/TensorRT-Model-Optimizer .

Performance using TensorRT 10.11

Timings for 30 steps at 1024x1024

Usage Example

1. Follow the setup instructions on launching a TensorRT NGC container.

git clone https://github.com/NVIDIA/TensorRT.git
cd TensorRT
git checkout release/10.11
docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:25.01-py3 /bin/bash

1. Install libraries and requirements

cd demo/Diffusion
python3 -m pip install --upgrade pip
pip3 install -r requirements.txt
python3 -m pip install --pre --upgrade --extra-index-url https://pypi.nvidia.com tensorrt-cu12==10.11.0

1. Generate HuggingFace user access token To download model checkpoints for the Stable Diffusion 3.5 checkpoints, please request access on the Stable Diffusion 3.5 Large page. You will then need to obtain a read access token to HuggingFace Hub and export as shown below. See instructions .

export HF_TOKEN=<your access token>

1. Perform TensorRT optimized inference:

• Stable Diffusion 3.5 Large in BF16 precision

  python3 demo_txt2img_sd35.py \
    "A chic urban apartment interior highlighting mid-century modern furniture, vibrant abstract art pieces on clean white walls, and large windows providing a stunning view of the bustling city below." \
    --version=3.5-large \
    --bf16 \
    --download-onnx-models \
    --denoising-steps=30 \
    --guidance-scale 3.5 \
    --build-static-batch \
    --use-cuda-graph \
    --hf-token=$HF_TOKEN
  

• Stable Diffusion 3.5 Large using FP8 quantization

  python3 demo_txt2img_sd35.py \
    "A chic urban apartment interior highlighting mid-century modern furniture, vibrant abstract art pieces on clean white walls, and large windows providing a stunning view of the bustling city below." \
    --version=3.5-large \
    --fp8 \
    --denoising-steps=30 \
    --guidance-scale 3.5  \
    --download-onnx-models \
    --build-static-batch \
    --use-cuda-graph \
    --hf-token=$HF_TOKEN \
    --onnx-dir onnx_fp8 \
    --engine-dir engine_fp8