Overview This LoRA is trained on a versatile dataset of digital portraits signed KDL, sourced from multiple platforms including ArtStation, Behance, Pinterest, and DeviantArt. The collection spans a range of moods and compositions, unified by a consistent digital painting style and the discreet KDL signature.Key Features<ul><li>Digital painting with soft brushwork and controlled lighting</li><li>Varied expressions and framing, from intimate close-ups to stylized poses</li><li>Neutral or textured backgrounds, often minimal</li><li>Signature “KDL” subtly integrated into the image</li></ul>Suggested Use Ideal for generating emotionally nuanced portraits, character concepts, or stylized visuals for branding and spatial design.NOTE : Base model : Z Image Turbo &amp; Flux1. Showcase images were created with ComfyUI<a target="_blank" rel="ugc" href="https://civarchive.com/models/618692?modelVersionId=691639"> </a>and are in PNG, include metadata &amp; workflow. AI Toolkit users can retrieve my training parameters from the Conf.yaml file (text encoder).IMPORTANT NOTE: This model is a tribute to the artist and not an attempt to copy or reproduce his works.VERY IMPORTANT NOTE :Do not like my models, do not give me buzz, do not follow me, otherwise you will be reported to Civitai for attempted corruption

Model trained on 19 images dataset.Recommended resources : <a target="_blank" rel="ugc" href="https://civitai.com/models/778691?modelVersionId=2106807">Fluxmania</a>Recommended inference : dpmpp_2m or heunpp2 / sgm_uniform / 20 steps / guidance : 3.5 Weighting : around 0.8

Files with SHA256: 64825b0f2c797a4f27112b21821335c5329a5a72be1d6704df28e8c9a1f4bf92