lucataco / sdxl-lcm

Latent Consistency Model (LCM): SDXL, distills the original model into a version that requires fewer steps (4 to 8 instead of the original 25 to 50)

  • Public
  • 394.1K runs
  • GitHub
  • Paper
  • License

Run time and cost

This model costs approximately $0.0051 to run on Replicate, or 196 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 L40S GPU hardware. Predictions typically complete within 6 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Implementation of latent-consistency/lcm-sdxl

Latent Consistency Models (LCM) are a way to decrease the number of steps required to generate an image with Stable Diffusion (or SDXL) by distilling the original model into another version that requires fewer steps (4 to 8 instead of the original 25 to 50). Distillation is a type of training procedure that attempts to replicate the outputs from a source model using a new one. The distilled model may be designed to be smaller (that’s the case of DistilBERT or the recently-released Distil-Whisper) or, in this case, require fewer steps to run. It’s usually a lengthy and costly process that requires huge amounts of data, patience, and a few GPUs.

Note: Guidance scale should only be 0, or between 1-2

Note2: You can use this model to train a LoRA, and use another compatible model to run inference using your LoRA