A beautiful asian girl. Weight 0.7-0.9. Add betterhands-vanilla LORA in positive prompt for better hands. Trained on CivitAi with 1000 images.

Positive prompt example : a beautiful photo of as1an, 1girl, detailed, 8k, masterpiece, realistic, eyelashes, ...

All poses were done without control-net because the model is also trained with various images of sitting, squatting, crouching or kneeling poses.

I hope you like it, I will see from your votes and pictures. If the result is positive (as I hope), I will continue to share other goodies.

In v2 semirealistic model is better. For upscale with realistic model is better use ITF.SkinDiffDetail-Lite-v1 at 2x. Trained with Semirealmix-v6 on Kohya_ss.

In v3 for SDXL (not Pony, not work) tested with StableYogi model. Trained on CivitAi. Weight 0.9. Adetailer mediapipe eyes only with same prompt and lora weight. Adetailer impaint mask blur 3, impaint denoising strenght 0.32.

IMPORTANT : If you appreciate the models, please consider leaving us a review and sharing the images generated using this model. Your feedback is valuable to both us and the AI community. Download only , without any evaluation it is not useful for me or for the community. If the model does not reach a correct ratio between downloads and votes will be removed. Thanks.

Recommended for a better result: ADETAILER mediapipe face mesh.

Setting : Sampling Euler-a or DPM Karras, HiresFix on, R-ESRGAN 4x+, Denoising 0.4, Upscale 2x, Sampling steps 35+, Resolution 512x768, Upscale 4x Ultra Sharp next passage.

It is strictly prohibited to distribute outside civitai this model or hosting services in third-party image generation services, or sell my images on other site. You can use this model for personal use on Civitai or A1111 on your pc. Not for sell.

If you like the character, always leave a vote and an image, and if you give some buzz you will allow me to train other LORA or MODEL.