Zara — a gorgeous young Persian woman with light brown wavy shoulder-length hair, striking hazel green eyes, delicate arched eyebrows, a soft round face with refined features, light olive skin with natural texture, strong athletic build with defined shoulders, natural C cup breastsThis LoRA captures Zara's face and identity for consistent renders across poses, outfits, andscenes. Retrained on the Krea 2 V30 base (RawRealDark_v2_V30) from a fresh 40-image identity setfor sharper identity lock and natural skin texture.Trigger word: zara_faceRecommended strength: 0.6 (0.4-0.8 range works; 0.6 is the sweet spot for face lock withoutidentity bleed)Works best with: Krea 2 base models. Photorealistic style, natural lighting.Example prompt:zara_face, a gorgeous young Persian woman with light brown wavy shoulder-length hair, striking hazel green eyes, delicate arched eyebrows, a soft round face with refined features, light olive skin with natural texture, strong athletic build with defined shoulders, natural C cup breasts, wearing a cream knit sweater, chest-up, warm smile, looking directly atthe camera, soft natural window lightingNegative prompt tips: avoid "bright" before eye colour (it can cause glowing eyes).This is a fictional character. All images are AI-generated. A matched slim-body LoRA is availableon this version for leaner silhouette shots.⭐ If these Zara renders hit the way you hoped, a rating and a 👍 on the previews would help morethan you'd think. Ten seconds, and it's the biggest boost an indie creator gets in search. Helpher get noticed. 🙏## Slim-body usage```- Stack with the face LoRA: face @ 0.6 + slim body @ 0.8, same seed- Use on booty/back/side shots for a leaner, flat-rear look- Skip it on front-facing shots or if you want the curvy silhouette- Works best on Krea 2 bases```## Review⭐ Enjoying Zara? A rating + 👍 on the previews makes a real difference to an indie creator. Merci!

Zara

v1.2 — V30 retrain.What changed: retrained from scratch on the Krea 2 V30 base (RawRealDark_v2_V30) using a fresh40-image identity set for sharper identity lock and more natural skin texture. Replaces theblend-trained face LoRA.Training: 16 epochs / DIM32 alpha32 on RawRealDark_v2_V30 — 40 images -&gt; 640 steps. Base: Krea 2.The companion body LoRA on this version is ALSO a fresh V30 retrain (DIM64 alpha64, onRawRealDark_v2_V30), uploaded as <code>zara_slim_body_v2_v30.safetensors</code>. It supersedes the previous body LoRA, which wastrained on a different base than the images it was shown with.Same trigger word (zara_face) — drop-in replacement, no prompt changes needed.Recommended strength: 0.6.Gallery: 20 images rendered on the V30 base with both LoRAs above.

Files with SHA256: 55314d729bca514a5b8cfcf19ad78f7a5fb12384dc546d87656736228fa8c244