Text-to-Image
TensorRT
ONNX
English
stable-diffusion
stable-diffusion-xl
stable-diffusion-xl-lcm
stable-diffusion-xl-lcmlora
Instructions to use stabilityai/stable-diffusion-xl-1.0-tensorrt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use stabilityai/stable-diffusion-xl-1.0-tensorrt with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Build dynamic shape
#9
by goker67 - opened
For dynamic shaping, I use the --build-dynamic-shape flag. But it outputs very small images. For example I give 512x768 for size, but it throws 64x96. How can I compile the model for dynamic shaping? My current command is look like:
"""
python3 code.py "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" --num-warmup-runs 1 --width 768 --height 512 --denoising-steps 25 --onnx-base-dir /workspace/stable-diffusion-xl-1.0-tensorrt/sdxl-1.0-base --repeat-prompt 2 --build-dynamic-shape
"""