Yori is an original character LoRA for Krea 2, trained without a trigger word.

The example images were generated with Lustify v10 Krea 2 Turbo INT8 ConvRot. This is the base model used for the previews, so use it if you want a similar overall look.

Recommended settings

• Trigger word: none — describe your scene normally.

• LoRA strength: 1.0

• Steps / CFG: 8 / 1.0

• Sampler / scheduler: Euler / simple

• Model sampling shift: 1.15

• No extra Turbo LoRA or style stack was used.

Rank 32 / alpha 32, BF16, approximately 235 MB. Trained on Krea 2 RAW; epoch 30 was selected after portrait, body, alternate-seed, profile and seated comparisons against held-out references.

Expressions, makeup, lighting and camera angles can change the apparent likeness. Exact clothing fit, body proportions and framing still depend on the prompt and seed; the examples show the actual results.

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 🙂