Re-trained on the same images but more strict prompting. Less makeup and jewelry, so you can choose which version you prefer. This version still produces some jewelry and makeup but far less than version one.
Miko Dai is a little-known ???? actress. She is 5'5, 108, 34A cup. You can search around online to find videos and photos of her. This Lora is built for local generation.
Version 2 is trained on 54 images using 4,000 steps and 50 samples per image. This version captions out her makeup. Still some remnants in generation but much less.
Use V1 for defaulted makeup
Use V2 for defaulted "no makeup"
Please note that all of my sample images double as a ComfyUI workflow! Simply drag any of the sample images into ComfyUI and it will open the entire workflow, set the seed, and use my same configuration. I typically use LLM generation but chose not to do so for these tests; instead, I used a more basic workflow.
Recommended settings:
Lora strength: 0.8-1.0
CFG guidance: 3.5
Sampler: DPM++ 2M, Beta
Steps: 35
Re-trained on the same images but more strict prompting. Less makeup and jewelry, so you can choose which version you prefer. This version still produces some jewelry and makeup but far less than version one.
1. Modèle partagé uniquement à l'apprentissage et au partage. Droits d'auteur et interprétation finale réservés à l'auteur original.
2. Auteur souhaitant revendiquer le modèle : Contactez officiellement SeaArt AI pour l'authentification. Nous protégeons les droits de chaque auteur. Cliquer pour revendiquer
