This style LoRA is based on the digital illustrations of David Lanham, known for his whimsical desktop wallpapers and character art. It produces quiet, minimal scenes: one small character or creature placed in a wide, simple landscape with plenty of empty space around it. Backgrounds are soft gradients or flat colour fields, such as deep night blues, pale mint greens and calm seascapes. The characters are cute and slightly odd, drawn with clean shapes, simple faces and gentle shading. Now and then the LoRA produces denser, more detailed pieces, but its main strength is a calm, storybook-like minimalism.
Trigger word: DlanhamStl
Usage
Put the trigger word first, then describe one small character and a simple setting.
Start at strength 0.8–1.0.
Wide aspect ratios such as 16:9 match the training images best, since most of them are wallpapers.
Words like “minimal”, “lots of negative space” and “soft gradient sky” help keep the clean look.
Busy prompts with many characters or detailed cities work against the style. Keep the scene simple.
Training details
Base model: Krea 2 Raw. Tested for inference on Krea 2 Turbo.
145 images, auto-captioned with Qwen3-VL.
1000 steps, rank 32, 768 px.
Example promptDlanhamStl, a tiny round blue creature with a red scarf standing alone on a calm shoreline at dusk, deep blue gradient sky, minimal composition, lots of empty space