Premium character LoRAs
Original synthetic characters, bundles and AI tools are in my shop:
Join the community on Discord: https://discord.gg/nB79wRNtMT
Cthulhu Characters
A style LoRA for Krea 2. Full-body concept art of investigators, cultists and creatures from the world of cosmic horror: 1920s clothes, lanterns and old books, dread in their eyes, painted with fine detail in muted, earthy colours.
Usage
Start the prompt with the trigger word CthulhuRK, then describe the subject and the scene as usual; the look comes from the LoRA.
Recommended weight: 1. Lower it to 0.7–0.8 to blend the style with other LoRAs. Made for Krea 2 Turbo (8 steps, CFG 1).
Prompt Examples
"A full-body character concept art of a 1920s private investigator, a character from the world of Call of Cthulhu: a rumpled trench coat, a fedora, a revolver and a lantern, eyes full of dread. Painterly digital illustration with fine detail, muted earthy colors, standing pose, a faint greenish glow from below. Tone of mystery and soft, eerie horror rather than gore. Plain light grey-beige background with a subtle shadow on the floor."
"A full-body character concept art of an antiquarian librarian from Miskatonic University, a character from the world of Call of Cthulhu: round glasses, a tweed suit and a forbidden tome bound in dark leather. Painterly digital illustration with fine detail, muted earthy colors, standing pose, a cold moonlight from one side. Tone of mystery and soft, eerie horror rather than gore. Plain light grey-beige background with a subtle shadow on the floor."
"A full-body character concept art of a robed cultist of Cthulhu, a character from the world of Call of Cthulhu: a hooded dark robe with green tentacle embroidery and a ritual dagger. Painterly digital illustration with fine detail, muted earthy colors, standing pose, a pale foggy light. Tone of mystery and soft, eerie horror rather than gore. Plain light grey-beige background with a subtle shadow on the floor."
Generation settings
Trained on Krea 2, and works on Krea 2 Turbo for faster generation.
- Raw: ~30 steps, guidance 3.5
- Turbo: ~8 steps, guidance 1.0
The gallery images were generated with krea2_turbo_mxfp8.safetensors, at 8 steps, guidance 1, LoRA weight 1.