Keltezaa/mckenna-grace-768-portrait

Mckenna Grace, 768 portrait

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

Prompt

(14-year-old:1.2) A High quality Photo of a 14-year-old girl, lips parted in a focused expression, black curly hair that is styled in a natural, tousled manner. The hair appears to be very short at the sides to medium length at the top and has a (voluminous on top of head). She is wearing (round thin wire rim glasses). Fair pale skin with freckles on nose and cheeks.

Prompt

(16-year-old:1.2) A High quality,muted tones, realistic, film noir, cinematic, Photo of a 16-year-old "ghostbuster" girl, natural beauty, white pale skin, light rosy lips parted with a focused expression, black curly hair that is tousled ant the top. The hair appears to be very short at the sides to medium length at the top and has a ( (voluminous, wavy and curly tousled on top of head:0.8)). She is wearing (round thin wire rim glasses). Fair pale skin with freckles on nose and cheeks. Wearing a "ghostbuster" overall and gear.

Model description

Specially for portraits and closeup portraits. Selected eyes look at camera. HD and sharp images selected to dataset. Used 100-150 photos.

Trained on Comfyui FluxTrainer on 16gb Vram

Better use resolution 768 (minimize face-body proportion distortions) and than upscale whatever you want.

Small size of LORA because of training only 2 blocks: 7 and 20.

Top line of the GRID is this checkpoint. Grids for lora strength 0.8 and 1.2

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/mckenna-grace-768-portrait', weight_name='mckenna_768_rank128_bf16-step03500.safetensors')
image = pipeline('Your custom prompt').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers