Readme
If you want 0 quality loss, you can set the cache_interval to 1.
If you want to do this yourself, visit: https://docs.pruna.ai/en/latest/tutorials_nb/flux_fast.html
This is an optimised version of the flux schnell model from black forest labs with the pruna tool. We achieve a ~3x speedup over the original model with minimal quality loss.
This model costs approximately $0.0018 to run on Replicate, or 555 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 2 seconds.
If you want 0 quality loss, you can set the cache_interval to 1.
If you want to do this yourself, visit: https://docs.pruna.ai/en/latest/tutorials_nb/flux_fast.html