Views
No views yet
| A100 80GB PCI | A100 80GB SXM | H100 80GB PCI | |
|---|---|---|---|
| VAE Encoder | 66.70 ms | 65.68 ms | 49.07 ms |
| CLIP | 105.41 ms | 53.20 ms | 91.32 ms |
| UNet x 25 | 30,367.73 ms | 27,489.88 ms | 19,102.98 ms |
| VAE Decoder | 4,663.63 ms | 4,544.12 ms | 3,382.62 ms |
| Total E2E | 35,258.38 ms | 32,166.41 ms | 22,644.73 ms |
1git clone https://github.com/rajeevsrao/TensorRT.git
2cd TensorRT
3git checkout release/svd
4
5git lfs install
6git clone https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1-tensorrt
7
8docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:23.12-py3 /bin/bash1cd demo/Diffusion
2python3 -m pip install --upgrade pip
3pip3 install -r requirements.txt
4python3 -m pip install --pre --upgrade --extra-index-url https://pypi.nvidia.com tensorrthuggingface-cli login1python3 demo_img2vid.py \
2 --version svd-xt-1.1 \
3 --onnx-dir /workspace/stable-video-diffusion-img2vid-xt-1-1-tensorrt \
4 --engine-dir engine-svd-xt-1-1 \
5 --build-static-batch \
6 --use-cuda-graph \
7 --input-image https://www.hdcarwallpapers.com/walls/2018_chevrolet_camaro_zl1_nascar_race_car_2-HD.jpg