POC of SDXL-LCM LoRA combined with a Replicate LoRA for 4 second inference time
This model costs approximately $0.0072 to run on Replicate, or 138 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 6 seconds. The predict time for this model varies significantly based on the inputs.
Call this with your Replicate LoRA via API:
import replicate
output = replicate.run(
"lucataco/sdxl-lcm-loras:48bdebc9f383f0e9f9e321e40c1ec7f08ac7b4dd49cf777646a6498c94605051",
input={"prompt": "A TOK emoji of a man", "replicate_weights": "https://pbxt.replicate.delivery/DUxxgRlwU5q3DNhaaEPnH70H6afeUh18iIFTZkbioqVWeoEjA/trained_model.tar", "seed": 23969},
)