Introduction of stable-diffusion-3.5-medium-tensorrt
Model Details of stable-diffusion-3.5-medium-tensorrt
Stable Diffusion 3.5 Medium TensorRT
Introduction
This repository hosts the
TensorRT-optimized version
of
Stable Diffusion 3.5 Medium
, developed in collaboration between
Stability AI
and
NVIDIA
. This implementation leverages NVIDIA's TensorRT deep learning inference library to deliver significant performance improvements while maintaining the exceptional image quality of the original model.
Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. The TensorRT optimization makes these capabilities accessible for production deployment and real-time applications.
Model Details
Model Description
This repository holds the ONNX exports of the T5, MMDiT and VAE models in BF16 precision.
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 Medium
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>
Perform TensorRT optimized inference:
Stable Diffusion 3.5 Medium in BF16 precision
python3 demo_txt2img_sd35.py \
"a beautiful photograph of Mt. Fuji during cherry blossom" \
--version=3.5-medium \
--bf16 \
--download-onnx-models \
--denoising-steps=30 \
--guidance-scale 3.5 \
--build-static-batch \
--use-cuda-graph \
--hf-token=$HF_TOKEN
Runs of stabilityai stable-diffusion-3.5-medium-tensorrt on huggingface.co
105
Total runs
0
24-hour runs
7
3-day runs
11
7-day runs
34
30-day runs
More Information About stable-diffusion-3.5-medium-tensorrt huggingface.co Model
More stable-diffusion-3.5-medium-tensorrt license Visit here:
stable-diffusion-3.5-medium-tensorrt huggingface.co is an AI model on huggingface.co that provides stable-diffusion-3.5-medium-tensorrt's model effect (), which can be used instantly with this stabilityai stable-diffusion-3.5-medium-tensorrt model. huggingface.co supports a free trial of the stable-diffusion-3.5-medium-tensorrt model, and also provides paid use of the stable-diffusion-3.5-medium-tensorrt. Support call stable-diffusion-3.5-medium-tensorrt model through api, including Node.js, Python, http.
stable-diffusion-3.5-medium-tensorrt huggingface.co is an online trial and call api platform, which integrates stable-diffusion-3.5-medium-tensorrt's modeling effects, including api services, and provides a free online trial of stable-diffusion-3.5-medium-tensorrt, you can try stable-diffusion-3.5-medium-tensorrt online for free by clicking the link below.
stabilityai stable-diffusion-3.5-medium-tensorrt online free url in huggingface.co:
stable-diffusion-3.5-medium-tensorrt is an open source model from GitHub that offers a free installation service, and any user can find stable-diffusion-3.5-medium-tensorrt on GitHub to install. At the same time, huggingface.co provides the effect of stable-diffusion-3.5-medium-tensorrt install, users can directly use stable-diffusion-3.5-medium-tensorrt installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
stable-diffusion-3.5-medium-tensorrt install url in huggingface.co: