Premium character LoRAs
Original synthetic characters, bundles and AI tools are in my shop:
Join the community on Discord: https://discord.gg/nB79wRNtMT
Crochet Famous
A style LoRA for Krea 2. Handmade crocheted amigurumi plushes: visible yarn stitches, chibi proportions with a big head, safety-bead eyes and tiny knitted accessories, photographed like a real craft piece. Describe the character or creature and its outfit, and the LoRA knits it.
Usage
Start the prompt with the trigger word CrochetFamousRK, 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
"CrochetFamousRK, Vertical image of a handmade crocheted amigurumi plush of Walter White as Heisenberg: black pork-pie hat, small glasses, goatee, green shirt under a beige jacket. Visible yarn stitches, chibi proportions with a big head, black safety-bead eyes, soft wool texture, held in two hands over a wooden table, a cozy room softly blurred behind, warm golden window light, shallow depth of field, realistic photo."
"CrochetFamousRK, Vertical image of a handmade crocheted amigurumi plush of Gandalf the Grey: long grey beard, pointed grey hat, grey robe, wooden staff. Visible yarn stitches, chibi proportions with a big head, black safety-bead eyes, soft wool texture, held in two hands over a wooden table, a cozy room softly blurred behind, warm golden window light, shallow depth of field, realistic photo."
"CrochetFamousRK, Vertical image of a handmade crocheted amigurumi plush of Captain Jack Sparrow: red bandana, tricorn hat, dreadlocks with beads, kohl-rimmed eyes, pirate coat. Visible yarn stitches, chibi proportions with a big head, black safety-bead eyes, soft wool texture, held in two hands over a wooden table, a cozy room softly blurred behind, warm golden window light, shallow depth of field, realistic photo."
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.