metadata

license: other
license_name: bespoke-lora-trained-license
license_link: >-
  https://multimodal.art/civitai-licenses?allowNoCredit=False&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=False
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
  - migrated
  - celebrity
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
widget:
  - text: ' '
    output:
      url: 30071437.jpeg
  - text: ' '
    output:
      url: 30071418.jpeg
  - text: ' '
    output:
      url: 30071419.jpeg
  - text: ' '
    output:
      url: 30071421.jpeg
  - text: ' '
    output:
      url: 30071422.jpeg
  - text: ' '
    output:
      url: 30071424.jpeg
  - text: ' '
    output:
      url: 30071434.jpeg
  - text: ' '
    output:
      url: 30071436.jpeg
  - text: ' '
    output:
      url: 30071439.jpeg
  - text: ' '
    output:
      url: 30072383.jpeg
  - text: ' '
    output:
      url: 30072384.jpeg
  - text: ' '
    output:
      url: 29865285.jpeg
  - text: ' '
    output:
      url: 29865282.jpeg

Mckenna Grace, 768 portrait

(CivitAI)

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