trigger = bell

My LoRA for American actress Kristen Bell, which is focused on photorealism and trained on 71 images from roughly the same years that the first three seasons of “Veronica Mars” originally aired (a period which also catches "Heroes", and leads right into her movies from the late aughts like "Forgetting Sarah Marshall", "Fanboys", "Couples Retreat", etc.)

All training images are at least 1024 x 1024 pixels and were trained for 5,000 steps using DrawThings AI.

My four sample images were generated with the LoRA on the following base models: SDXL Base Model (v1.0) (Veronica hat portrait), cinemaxAlphaSDXLCinema_alpha1 (short hair widescreen), RealVisXL V4.0 (portrait standing in a doorway) and cinemaxAlphaSDXLCinema_alpha1 (long hair widescreen). I usually apply this LoRA by itself at 1.0, but you may want to bump up or down for effect or based on other resources.

Please use this LoRA of a real person legally and responsibly, and enjoy!