LoRA of Valensiya S. (For SDXL)

Description

This LoRA trained using kohya_ss on 60 images 1024×1024 up to 7200 steps without captions and with regularization images.
Source model: ‘Source model: SD-XL_1.0-base,’ so this LoRA should works well with most of SDXL family checkpoints.
learning rate: 0.00003.
Precision: fp16.
LR Scheduler: constant_with_warmup.
LR warmup: 30%.

Preview image generation data:
Positive Prompt: Masterpiece, Fashion, High quality, 64K, Unity 64K Wallpaper, HDR, Best Quality, RAW, Super Fine Photography, Super High Resolution, Super Detailed, Beautiful and Aesthetic, Stunningly beautiful, Perfect proportions.
Artistic photo of a beautiful little girl. Professional studio headshot of a stunning AIDA_XLLR_valenss with her blonde hair in two ponytails, she is wearing a pink dress and little pearl earrings. Ten years old girl with puked lips and smooth skin. She is in playful and relaxed mood, she is looking at the camera with serious look on her face. Puffy lips. Puked lips. Pretty symmetrical face with big beautiful brown eyes and long elegant eyelashes. Dramatic colorful light, blue key light and yellow fill light creating a balanced exposure. Clean, black background, 50mm lens for a natural look, confident stance, looking directly at the camera, depth of field.
Sharp focus, Perfect facial features, Pure and pretty, Perfect eyes, Lively eyes, Elegant face, Delicate face, Exquisite face, more detail XL, photo-real, accurate ears anatomy, elegant ears.
Negative prompt: braids, braided hair, headband, head wear, bow, hair clips, make up, makeup, lipstick, noisy, film grain, jpeg artifacts, bad anatomy, bad hands, missing arms, extra hands, extra fingers, bad fingers, extra legs, missing legs, poorly drawn face, fused face, worst feet, extra feet, fused feet, fused thigh, extra thigh, worst thigh, missing fingers, long fingers, extra eyes, huge eyes, amputation, cartoon, cg, 3d, unreal, animate, cropped, blurry, adult
Steps: 20,
Sampler: DPM++ SDE,
Schedule type: Karras,
CFG scale: 3,
Seed: 3510867431,
Size: 1024×1024,
Model hash: 934c946922, Model: BastardV1.safetensors,
VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.safetensors,
Clip skip: 2,
Hires upscale: 1.5,
Hires steps: 20,
Hires upscaler: 4x_NMKD-Siax_200k
Lora value: 0.9, Lora name and hash: “AIDA_XLLR_valenss: e99c0db399a3”,
Refiner: sdvn6Realxl_detailface.safetensors [777f31751a],
Refiner switch at: 0.9

Download link to AIDA_XLLR_valenss.safetensors will be available for you after purchase. For your comfort I packed AIDA_XLLR_valenss.safetensors into .zip archive with AIDA_XLLR_valenss.png and AIDA_XLLR_valenss.txt, preview and description are compatible with AUTOMATIC1111 extra networks menu.

Purchasing this asset you will achieve rights for selling images generated with AIDA_XLLR_valenss.safetensors LoRA. If you want say special thanks to me, you can add additional amount to your payment.

Please contact me if you need some extended rights for sharing or selling AIDA_XLLR_valenss, merging AIDA_XLLR_valenss with other models, using AIDA_XLLR_valenss in generation services and so on.