Skip to content

Convert and inference T2I-Adapter models in ONNX and TensorRT

Notifications You must be signed in to change notification settings

ffletcherr/t2i-adapter-trt

 
 

Repository files navigation

T2I Adapter Diffusers + ONNX + TensorRT

Convert and Inference T2I-Adapter models in ONNX and TensorRT. Polygraphy is used to convert from onnx to tensorrt and create engine file.

see t2i_adapter_trt.ipynb

Open In Colab


Original Image Converted by Canny Adapter

References

convert_stable_diffusion_checkpoint_to_onnx.py

t2i-adapter-diffusers

T2I-Adapter

@misc{https://doi.org/10.48550/arxiv.2302.08453,
  doi = {10.48550/ARXIV.2302.08453},
  url = {https://arxiv.org/abs/2302.08453},
  author = {Mou, Chong and Wang, Xintao and Xie, Liangbin and Zhang, Jian and Qi, Zhongang and Shan, Ying and Qie, Xiaohu},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), Artificial Intelligence (cs.AI), Machine Learning (cs.LG), Multimedia (cs.MM), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International}
}

About

Convert and inference T2I-Adapter models in ONNX and TensorRT

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 84.0%
  • Python 16.0%