Readme
About
Cog Implementation of the model: SG161222/RealVisXL_V2.0 with LCM LoRA for faster inference speeds
RealvisXL-v2.0 with LCM LoRA - requires fewer steps (4 to 8 instead of the original 40 to 50)
This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 3 seconds.
Cog Implementation of the model: SG161222/RealVisXL_V2.0 with LCM LoRA for faster inference speeds