metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
widget:
  - text: >-
      caricature of  a girl wearing a tweed suit, lithography, by Honoré Daumier
      <lora:honore_daumier_sdxl_v1-000014:1.0>
    output:
      url: images/00154-480187136.png
  - text: >-
      caricature of  a boy wearing a superhero costume, lithography, by Honoré
      Daumier <lora:honore_daumier_sdxl_v1-000014:1.0>
    output:
      url: images/00132-480187136.png
  - text: >-
      caricature of  a dog wearing a police uniform, lithography, by Honoré
      Daumier <lora:honore_daumier_sdxl_v1-000014:1.0>
    output:
      url: images/00141-480187136.png
  - text: >-
      caricature of  a frog wearing a police uniform, lithography, by Honoré
      Daumier <lora:honore_daumier_sdxl_v1-000014:1.0>
    output:
      url: images/00143-480187136.png
  - text: >-
      caricature of  an alien, lithography, by Honoré Daumier
      <lora:honore_daumier_sdxl_v1:1.0>
    output:
      url: images/00162-2919928779.png
  - text: >-
      caricature of  a viking warrior, lithography, by Honoré Daumier
      <lora:honore_daumier_sdxl_v1:1.0>
    output:
      url: images/00173-1015849521.png
  - text: >-
      caricature of  a basketball player, lithography, by Honoré Daumier
      <lora:honore_daumier_sdxl_v1:1.0>
    output:
      url: images/00174-1135926644.png
  - text: >-
      caricature of  a cyborg robot, lithography, by Honoré Daumier
      <lora:honore_daumier_sdxl_v1:1.0>
    output:
      url: images/00163-364911675.png
  - text: >-
      caricature of  an eagle, lithography, by Honoré Daumier
      <lora:honore_daumier_sdxl_v1:1.0>
    output:
      url: images/00179-3969836619.png
  - text: >-
      caricature of  a cowboy, lithography, by Honoré Daumier
      <lora:honore_daumier_sdxl_v1:1.0>
    output:
      url: images/00190-4023438497.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: caricature, lithography by Honoré Daumier
license: cc-by-nc-4.0

Honoré Daumier

Prompt
caricature of a dog wearing a police uniform, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt
caricature of a frog wearing a police uniform, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt
caricature of an alien, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt
caricature of a viking warrior, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt
caricature of a basketball player, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt
caricature of a cyborg robot, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt
caricature of an eagle, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt
caricature of a cowboy, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Model description

Daumier LoRA Model

This model card represents a LoRA (Low-Rank Adaptation) model trained on the Honoré Daumier Dataset available at Honoré Daumier Dataset. The model is adept at generating and analyzing satirical lithographic caricatures with exaggerated features, typical of Daumier's style.

Model Overview

The Daumier LoRA model has been trained to capture the essence of Honoré Daumier's satirical lithographs, which feature prominent 'big head' caricatures that are well-known for their social and political commentary during the 19th century.

Training Configuration

Dataset: Honoré Daumier Dataset
Epochs: 14
Number of Images: 67
Repeats per Image: 10 (Each image was presented ten times throughout the training process to enhance detail recognition)
Optimizer: DAdaptAdam (Chosen for its robustness in LoRA model training)
Precision: bf16 (Balances computational performance with memory efficiency)
Main Trigger: The model is fine-tuned to recognize and replicate Daumier's unique caricature style.
Xformers: Implemented for more efficient transformer model operations
Captioning Method: GPT-Vision (Employs GPT-Vision to generate captions that guide the AI's learning process), with token shuffling for improved training
Base Model: Stable Diffusion XL 1.0 (Used for its advanced capabilities in detailed image generation)

Model Usage

The Daumier LoRA model is specifically trained to generate images that replicate the satirical and exaggerated style characteristic of Honoré Daumier's lithographs.

Performance and Limitations

Performance: The model performs effectively in generating caricatures with exaggerated features and capturing the satirical essence of Daumier's artwork.
Limitations: Given the specific focus of the dataset on Daumier's work, the model may not generalize well to other styles of caricature or art forms.

Ethical Considerations

Intended Use: Intended for non-commercial applications such as art historical education, pattern recognition in artwork, and digital art creation.
Bias and Fairness: The model reflects the societal and cultural biases present in 19th-century France as depicted in Daumier's work.

Licensing

Model License: This model is licensed under Creative Commons Attribution-NonCommercial 4.0 Generic (CC BY-NC 4.0) for non-commercial use.
Dataset License: The Honoré Daumier Dataset is licensed under CC BY-NC 2.0.

Contributions and Feedback

We invite feedback and contributions to further refine the model's capabilities. Visit the model's page on Hugging Face for more information on how you can contribute or provide feedback.

Trigger words

You should use caricature to trigger the image generation.

You should use lithography by Honoré Daumier to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.