README.md

metadata

license: apache-2.0
library_name: pruna-engine
thumbnail: >-
  https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg
metrics:
  - memory_disk
  - memory_inference
  - inference_latency
  - inference_throughput
  - inference_CO2_emissions
  - inference_energy_consumption

Simply make AI models cheaper, smaller, faster, and greener!

• Give a thumbs up if you like this model!
• Contact us and tell us which model to compress next here.
• Request access to easily compress your own AI models here.
• Read the documentations to know more here
• Share feedback and suggestions on the Slack of Pruna AI (Coming soon!).

Results

These results were obtained on NVIDIA A100-PCIE-40GB with configuration described in config.json. Results may vary in other settings (e.g. other hardware, image size, batch size, ...).

Setup

You can run the smashed model with these steps:

0. Check that you have cuda installed. You can do this by running nvcc --version or conda install nvidia/label/cuda-12.1.0::cuda.
1. Install the pruna-engine available here on Pypi. It might take 15 minutes to install.

   pip install pruna-engine[gpu] --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com
   

2. Download the model files using one of these three options.
   • Option 1 - Use command line interface (CLI):

     mkdir runwayml-stable-diffusion-v1-5-turbo-tiny-green-smashed
     huggingface-cli download PrunaAI/runwayml-stable-diffusion-v1-5-turbo-tiny-green-smashed --local-dir runwayml-stable-diffusion-v1-5-turbo-tiny-green-smashed --local-dir-use-symlinks False
     

   • Option 2 - Use Python:

     import subprocess
     repo_name = "runwayml-stable-diffusion-v1-5-turbo-tiny-green-smashed"
     subprocess.run(["mkdir", repo_name])
     subprocess.run(["huggingface-cli", "download", 'PrunaAI/'+ repo_name, "--local-dir", repo_name, "--local-dir-use-symlinks", "False"])
     

   • Option 3 - Download them manually on the HuggingFace model page.
3. Load & run the model.

   from pruna_engine.PrunaModel import PrunaModel
   
   model_path = "runwayml-stable-diffusion-v1-5-turbo-tiny-green-smashed/model"  # Specify the downloaded model path.
   smashed_model = PrunaModel.load_model(model_path)  # Load the model.
   smashed_model(prompt='Beautiful fruits in trees', image_height=1024, image_width=1024)[0][0]  # Run the model where x is the expected input of.
   

Configurations

The configuration info are in config.json.

License

We follow the same license as the original model. Please check the license of the original model ORIGINAL_runwayml-stable-diffusion-v1-5-turbo-tiny-green-smashed before using this model.

Want to compress other models?

• Contact us and tell us which model to compress next here.
• Request access to easily compress your own AI models here.