Banunga_sdxl_lora

Kenza Né Banunga

<Gallery />

• Model Card for Kenza Né Banunga LoRA SDXL

Example of generated images:

<img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/8QRnQTayPEPWvVZt80EFU.png" alt="Generated Image" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/T_Kxg2l9EPpHzVXVZPvmY.png" alt="Generated Image" width="400"/>

<img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/uvQZz7AhPy8Er8W5SK-O5.png" alt="Generated Image" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/idi_7XzAlpa8w2QLMgVrP.png" alt="Generated Image 1" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/Uv1J--7rqPSjCT-Qamg1Z.png" alt="Generated Image 2" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/k0m-7UNegFU8pVNMPicsA.png" alt="Generated Image 3" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/HW0KkejvBkmIyN8DnfElU.png" alt="Generated Image 4" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/fG35p5nNet2m_IxvMYJfF.png" alt="Generated Image 5" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/h6rAhiRl7L3hN43f4XYAa.png" alt="Generated Image 6" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/2WHnYa8LclxRc5eHX-eyV.png" alt="Generated Image 7" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/3DlMGY0fvNui0B6by5aD9.png" alt="Generated Image 8" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/UTyBj1ysydShzIwtOHfZi.png" alt="Generated Image 9" width="400"/>

Details:

Description:

This model is a Low-Rank Adaptation (LoRA) trained to generate images of a young woman named Kenza Né Banunga. 
It is designed to be used with Stable Diffusion XL models to create photorealistic images of this specific character.

developed_by: Anonymous

finetuned_from: frankjoshua/realvisxlV40_v40Bakedvae

repository: local

• Trained on Kohya_ss Arch-Linux

Usage:

Direct_use:

This LoRA can be used with compatible SDXL models to generate photorealistic images of Kenza Né Banunga in various situations and poses.

Out_of_scope_use:

This model should not be used to create explicitly sexual, defamatory, or harmful images.

Bias risks limitations:

Description:

The model may have biases in the representation of physical traits and facial expressions. 
The quality of results may vary depending on the base model used.

Recommendations:

Users should be aware of potential biases and use the model responsibly and ethically.

Training details:

Training_data: local

Training_procedure:

Hyperparameters:
  training_regime: bf16 mixed precision
  epochs: 30
  learning_rate: 1e-05
  train_batch_size: 3
  gradient_accumulation_steps: 1
  optimizer: AdamW
  lr_scheduler: constant
  lora_rank: 32
  network_alpha: 128
  resolution: 1024x1024 max
checkpointing:
  save_every_n_steps: 30
  save_at_epoch_end: true

Technical specifications:

Model_architecture:

type: LoRA Standard
base_model: SDXL
gradient_checkpointing: true
xformers: enabled

Compute_infrastructure:

 hardware: NVIDIA GPU GEFORCE RTX-3060
 software: Kohya_ss
  framework: PyTorch with xformers
  precision: bf16 mixed precision

Additional_information:

Training_comment:

3 repeats. More info: https://civitai.com/articles/1771 2_3_Kenza_Né_Banunga woman 35 epoch

Model card:

Authors: Anonymous

Contact: Information not available

Use it with the 🧨 diffusers library

usage example: |

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    'frankjoshua/realvisxlV40_v40Bakedvae', 
    torch_dtype=torch.float16
).to('cuda')
pipeline.load_lora_weights('path/to/Kenza_Né_Banunga_Lora_SDXL_dim32x128', weight_name='pytorch_lora_weights.safetensors')
image = pipeline('your prompt').images

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