Kimy - Krea 2 OC
Kimy is a photorealistic original character LoRA for Krea 2, made for portraits, casual photography and varied outfits and scenes.
Example images were generated with Lustify v10 Krea 2 Turbo (INT8 ConvRot). The LoRA itself was trained on Krea 2 RAW. No additional style or Turbo LoRA was used in the examples.
Recommended starting settings
LoRA strength: 1.0
No trigger word required
Lustify v10 Krea 2 Turbo: 8 steps, CFG 1
Sampler: Euler; scheduler: Simple
Use natural-language prompts describing the outfit, pose, framing and lighting you want.
This release uses epoch 20, selected by visual likeness comparisons from a 30-epoch run. Rank 32 / alpha 32, BF16, approximately 235 MB. Training used 119 curated images, with 20 separate reference images held out for evaluation.
Faces can vary with the prompt, seed, angle and expression. Exact garment fit and body proportions are not guaranteed; detailed framing and clothing descriptions help. These settings are the tested starting point, not a guarantee of identical results.
Commissions
Hey! Could really use some extra money rn, so I’m offering paid help with ComfyUI and local AI stuff:
Fix broken workflows and custom nodes
Build custom workflows and small custom nodes
Train LoRAs to order and prepare datasets
Set up ComfyUI, models and dependencies
Optimize speed and VRAM usage where possible
Automate batch generation and repetitive tasks
Set up upscaling, inpainting and background removal
DM me with what you need + your GPU. I’ll confirm what I can do and the price before starting 🙂
Description
Initial release: epoch 20 / 2,380 training steps, selected from a 30-epoch comparison. Trained on Krea 2 RAW; example images use Lustify v10 Krea 2 Turbo INT8 ConvRot at strength 1.0, 8 steps, CFG 1, Euler/simple, shift 1.15. No trigger word, extra Turbo adapter or style stack. Rank 32 / alpha 32; BF16.





