metadata

license: openrail
language:
  - en
metrics:
  - character
pipeline_tag: text-to-image
tags:
  - lora
  - stable-diffusion-xl
  - image-generation
base_model:
  - SG161222/RealVisXL_V4.0
instance_prompt: Kenza_Né_Banunga
widget:
  - text: >-
      long shot scenic professional photograph of urban graffiti style
      professional 3d model A vibrant portrait captures the captivating essence
      of Kenza Né Banunga, confidently posing in front of a striking backdrop,
      photographed by the talented Nina Masic. The model showcases an iconic
      look inspired by the street style of Harlem in the early '90s:
      high-waisted baggy jeans, a colorful crop top, and an oversized denim
      jacket. Her hair is styled in voluminous box braids adorned with gold
      beads. Bold hoop earrings and a pair of Timberland boots complete her
      urban ensemble.
    parameters:
      negative_prompt: >-
        ugly, deformed, noisy, low poly, blurry, painting, clean, minimalistic,
        soft, gentle, blurry, off-center
    output:
      url: >-
        https://cdn-uploads.huggingface.co/production/uploads/64a9a333e368492ab8dfccae/JX-CBAi-ZTuAuPR7MuqgO.png
  - text: >-
      Kenza_Né_Banunga A captivating image captures the vibrant atmosphere of a 
      high-profile sports event: the NBA Basket Final. In this full-body shot, 
      the subject is a Kenza woman standing confidently in front of a dramatic 
      backdrop, radiating energy and confidence amidst the excitement
      surrounding one of basketball's most coveted competitions.
    output:
      url: images/ComfyUI_02150_.png
  - text: >-
      Kenza_Né_Banunga woman  full-body shot, rapper pose, curved woman braided
      hair,  black, brown, grin, hair, nail, white leather jacket with round
      collar, black  tshirt and white skirt photoshot 
    output:
      url: images/ComfyUI_02159_.png
  - text: >-
      Kenza_Né_Banunga woman  full-body shot, rapper pose, curved woman braided
      hair,  black, brown, grin, hair, nail, white leather jacket with round
      collar, black  tshirt and white skirt photoshot, empty MADISON SQUARE
      GARDEN, outdoors
    output:
      url: images/ComfyUI_02170_.png
library_name: diffusers

Kenza Né Banunga

Prompt
long shot scenic professional photograph of urban graffiti style professional 3d model A vibrant portrait captures the captivating essence of Kenza Né Banunga, confidently posing in front of a striking backdrop, photographed by the talented Nina Masic. The model showcases an iconic look inspired by the street style of Harlem in the early '90s: high-waisted baggy jeans, a colorful crop top, and an oversized denim jacket. Her hair is styled in voluminous box braids adorned with gold beads. Bold hoop earrings and a pair of Timberland boots complete her urban ensemble.

Negative Prompt
ugly, deformed, noisy, low poly, blurry, painting, clean, minimalistic, soft, gentle, blurry, off-center

Prompt
Kenza_Né_Banunga woman full-body shot, rapper pose, curved woman braided hair, black, brown, grin, hair, nail, white leather jacket with round collar, black tshirt and white skirt photoshot

Model Card for Kenza Né Banunga LoRA SDXL

Example of generated images:

Generated Image Generated Image 1 Generated Image 2 Generated Image 3 Generated Image 4 Generated Image 5 Generated Image 6 Generated Image 7 Generated Image 8 Generated Image 9

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