Image
Collection
text-to-image and image-to-image models
•
8 items
•
Updated
•
67
This repository hosts the TensorRT version of Stable Diffusion XL Turbo created in collaboration with NVIDIA. The optimized versions give substantial improvements in speed and efficiency.
SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation. A real-time demo is available here: http://clipdrop.co/stable-diffusion-turbo
SDXL-Turbo is a distilled version of SDXL 1.0, trained for real-time synthesis.
Accelerator | CLIP | Unet | VAE | Total |
---|---|---|---|---|
A100 | 1.03 ms | 79.31 ms | 53.69.34 ms | 138.57 ms |
H100 | 0.78 ms | 48.87 ms | 30.35 ms | 83.8 ms |
git clone https://github.com/rajeevsrao/TensorRT.git
cd TensorRT
git checkout release/9.2
docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:23.11-py3 /bin/bash
git lfs install
git clone https://huggingface.co/stabilityai/sdxl-turbo-tensorrt
cd sdxl-turbo-tensorrt
git lfs pull
cd ..
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
SDXL Turbo
Works best for 512x512 images and EulerA scheduler. The first invocation produces plan files in --engine-dir specific to the accelerator being run on and are reused for later invocations.
python3 demo_txt2img_xl.py \
""Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"" \
--version=xl-turbo \
--onnx-dir /workspace/sdxl-turbo-tensorrt/ \
--engine-dir /workspace/sdxl-turbo-tensorrt/engine \
--denoising-steps 4 \
--guidance-scale 0.0 \
--seed 42 \
--width 512 \
--height 512