Blib-la/thomas_rowlandson_lora_sdxl

Thomas Rowlandson

Prompt

a lizard riding a bicycle in space, hand colored etching, by thomas rowlandson <lora:thomas_rowlandson_sdxl_v1-000020:1.0>

Prompt

a cyborg robot sitting on the couch watching television while eating a cake, hand colored etching, by thomas rowlandson <lora:thomas_rowlandson_sdxl_v1-000020:1.0>

Prompt

a kangaroo riding jet-skis on the lake, hand colored etching, by thomas rowlandson <lora:thomas_rowlandson_sdxl_v1-000020:1.0>

Prompt

a frog sitting in a chair watching television and eating a soup, hand colored etching, by thomas rowlandson <lora:thomas_rowlandson_sdxl_v1-000020:1.0>

Prompt

a chameleon wearing a superhero costume, hand colored etching, by thomas rowlandson <lora:thomas_rowlandson_sdxl_v1-000020:1.0>

Prompt

a monkey selling bananas in the jungle, hand colored etching, by thomas rowlandson <lora:thomas_rowlandson_sdxl_v1-000020:1.0>

Model description

---

Model Overview

This model card introduces the Rowlandson Visions LoRA (Low-Rank Adaptation) model, trained on the Thomas Rowlandson Hand-Colored Etchings Collection. Accessible from our Thomas Rowlandson Collection, this model is tailored to recognize, analyze, and generate imagery inspired by Thomas Rowlandson's distinctive hand-colored etchings. These artworks, originating from the late 18th to early 19th century, offer a satirical and picturesque view of British life, society, and landscapes. The Rowlandson Visions LoRA model captures the essence of Rowlandson's artistry, enabling the generation of images that reflect his unique style and thematic focus.

Training Configuration

• Dataset: Thomas Rowlandson Collection
• Epochs: 20
• Number of Images: 80
• Repeats per Image: 10 (Employing each image multiple times during training to deepen model understanding)
• Optimizer: DAdaptAdam (Chosen for its adaptability and performance with LoRA models)
• Precision: bf16 (For a balanced approach to computational efficiency and memory management)
• Main Trigger: Activation by the phrase "hand painted etching by thomas rowlandson" to generate images reflecting Rowlandson's style.
• Xformers: Utilized to improve transformer model operations
• Captioning Method: Employing GPT-Vision with captions designed for token shuffling to maximize learning outcomes
• Base Model: Built on the foundation of Stable Diffusion XL 1.0, known for its intricate and nuanced image generation

Model Usage

The Rowlandson Visions LoRA model excels in producing images that mimic Thomas Rowlandson's renowned hand-colored etchings. It serves as a powerful tool for exploring historical art styles, educational purposes, and artistic inspiration, offering insights into British culture and humor of the era.

Performance and Limitations

• Performance: Demonstrates a robust capability to generate art that aligns with Rowlandson's hand-colored etchings, capturing the humor and critique of British society.
• Limitations: Given the dataset's focus on Rowlandson's work, the model might not fully encompass the broader spectrum of 18th and 19th-century art styles.

Ethical Considerations

• Intended Use: Crafted for scholarly, educational, and non-commercial creative endeavors, aiming to foster appreciation and understanding of historical art.
• Bias and Fairness: Reflects biases inherent in Rowlandson's subjects and perspectives, indicative of his time's societal attitudes.

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 welcome and value your contributions to improve the model and feedback regarding its performance. For further engagement, visit the model's Hugging Face page to share your insights or contribute.

Trigger words

You should use hand painted etching by thomas rowlandson 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.