Blib-la/honore_daumier_lora_sdxl

Honoré Daumier

Prompt

caricature of a girl wearing a tweed suit, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

Prompt

caricature of a boy wearing a superhero costume, lithography, by Honoré Daumier <lora:honore_daumier_sdxl_v1:1.0>

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: Licensed under Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND 4.0) for non-commercial use.

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.

Related

https://blib.la/blog/crafting-the-future-blibla-s-ethical-approach-to-ai-model-training

Additional Usage Restrictions for Blibla's LoRAs Hosted on Hugging Face

In alignment with our commitment to ensuring the responsible and ethical use of our models, and in addition to the terms set forth in the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0) under which Blibla's LoRAs are licensed, we hereby impose the following specific restrictions:

1. Prohibited Platforms: Reuploading, redistributing, or offering of image generation services using our models on platforms not owned or operated by Blibla or Hugging Face is strictly forbidden. This includes, but is not limited to, any platforms that host, allow, or promote Not Safe For Work (NSFW) content.

2. Explicitly Forbidden Platforms: For clarity, and without limiting the generality of the above, platforms including but not limited to Leonardo AI, Civit AI, and any "Hugging Face spaces" that host or permit NSFW content are explicitly prohibited from hosting, or utilizing Blibla's LoRAs in any form or manner.

3. Responsibility of Users: Users of Blibla's LoRAs are responsible for ensuring that the environments in which they use, share, or promote our models adhere strictly to these restrictions. Violation of these terms may result in revocation of the license granted under CC BY-NC-ND 4.0 and may prompt further legal action to protect the integrity of our models and the safety of the communities we serve.

4. Purpose of Restrictions: These restrictions are put in place to align with Blibla's ethical standards and the intended use of our models. They are designed to prevent associations with content or platforms that do not reflect our values or the intended application of our technology.

By utilizing Blibla's LoRAs, you acknowledge and agree to these additional restrictions, ensuring that the use of our models remains within the bounds of ethical and responsible practice.