---
license: apache-2.0
---
This is [fal/AuraFlow](https://huggingface.co/fal/AuraFlow), converted from FP16 to 8-bit. Small or one-dimensional tensors are left in FP16 so as to avoid severe degredation.

This is an experimental conversion and I don't have currently have enough memory to run this locally, so it is not guaranteed to work. Please let me know if it works or not.

**In order to actually save memory usage you will need to prevent your inference engine from upcasting to FP16 during calculation.**

The code used to convert the model is in the repo as well.

Enjoy!