This model is based on SDXL so will only work with SDXL-based checkpoints.
Recommended checkpoint: RealVisXL
Recommended ControlNets: xinsir depth + canny models
Included 20+ sample images with prompts and settings embedded inside the pngs.
Run with your favourite image diffusion UI (automatic1111, comfyUI, forgeUI, fooocus or online services like rundiffusion)
For a guide on how to install and run this model locally and online click here: Guide on how to run f-f models
More info about LoRAs for architecture design workflows here: f-f LoRAs