Unless otherwise stated, the previews are raw outputs (no Adetailler/HiresFix)

V1 is the base lora model

CompressedV1 is near V1 model results and is almost 2x smaller

CompressedV2 can produce interesting results and is almost 10x smaller than V1

Follow me on X if you want to be informed when a new model is published: https://x.com/AeremAi