Blib-la/eugene_atget_lora_sdxl

Eugene Atget

Captain: The AI platform that evolves to your needs

• 🚀 Check out Captain
• 👩‍💻 Captain on GitHub

Prompt

a antique photograph of a woman wearing a superhero costume, by eugene atget, monochrome <lora:eugene_atget_sdxl_v1:1>

Prompt

a antique photograph of a cat wearing a superhero costume, by eugene atget, monochrome <lora:eugene_atget_sdxl_v1:1>

Prompt

a antique photograph of a woman wearing a space suit, by eugene atget, monochrome <lora:eugene_atget_sdxl_v1:1>

Prompt

a antique photograph of a girl wearing a police uniform, by eugene atget, monochrome <lora:eugene_atget_sdxl_v1:1>

Prompt

a antique photograph of a boy wearing a clown costume, by eugene atget, monochrome <lora:eugene_atget_sdxl_v1:1>

Prompt

a antique photograph of a dog wearing a clown costume, by eugene atget, monochrome <lora:eugene_atget_sdxl_v1:1>

Model Overview

This model card details a LoRA (Low-Rank Adaptation) model trained on the Eugene Atget Dataset, which is accessible from our Eugene Atget Dataset collection. The model specializes in generating and analyzing historical urban imagery, particularly from the early 1900s Parisian scenes captured by Eugène Atget. The Atget Visions LoRA model is fine-tuned to identify and recreate the unique photographic style of Eugène Atget, characterized by its detailed depiction of Parisian architecture, streets, and daily life at the turn of the 20th century.

Training Configuration

• Dataset: Eugene Atget Dataset
• Epochs: 17
• Number of Images: 31
• Repeats per Image: 10 (Each image was used 10 times during training to ensure depth in learning)
• Optimizer: DAdaptAdam (Specifically chosen for its efficiency in training LoRA models)
• Precision: bf16 (Optimal balance of performance and memory usage)
• Main Trigger: The model is triggered by the phrase "by eugene atget" to generate images in the style of the photographer.
• Xformers: Enabled for enhanced efficiency in transformer models
• Captioning Method: GPT-Vision, with captions optimized for token shuffling for enhanced learning
• Base Model: Stable Diffusion XL 1.0, renowned for its detailed and nuanced image generation capabilities

Model Usage

This LoRA model is adept at replicating the distinctive photographic style of Eugène Atget, useful for historical image analysis, artistic studies, and education in the realm of early photography.

Performance and Limitations

• Performance: Exhibits a strong ability to generate images with a historical and artistic aesthetic akin to Atget's work.
• Limitations: With a focused dataset of 31 images, the model may not cover the full breadth of Atget's portfolio or the variability of early 20th-century Parisian imagery.

Ethical Considerations

• Intended Use: The model is designed for non-commercial purposes, particularly useful in historical research, art analysis, and education.
• Bias and Fairness: The dataset may contain biases towards the specific subjects and styles present in Atget's photography, reflecting the era's socio-cultural context.

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

Contributions to enhance the model and feedback on its performance are greatly appreciated. Please visit the model's page on Hugging Face to provide your input or to contribute.

Trigger words

You should use by eugene atget 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.