LoRA
Custom LoRA
A style or identity adapter trained on your material and tuned until it actually holds.
Send 30–300 reference images. We curate, caption, train and evaluate against a held-out set, then iterate until identity or style holds at usable weights. You get the safetensors and the training card.
- 30–300 images
- SDXL or FLUX.2
- safetensors + card
- until eval passes
$799
Pay now and a brief form arrives by email so we can start.
Rights negotiated per project and confirmed in writing before work starts.