soda_can_lora_sdxl

Soda Can LoRA SDXL

Captain: The AI platform that evolves to your needs

• 🚀 Check out Captain
• 👩‍💻 Captain on GitHub

<Gallery />

Model Overview

This model card introduces the LoRA (Low-Rank Adaptation) model trained on the Soda Can Dataset, sourced from our Soda Can Dataset. The model excels in generating high-fidelity images of soda cans under various conditions and settings.

Training Configuration

• Dataset: Soda Can Dataset
• Epochs: 10
• Number of Images: 200
• Repeats per Image: 10 (Each image was used 10 times during training)
• Optimizer: DAdaptAdam (Tailored for efficient and impactful AI model training)
• Precision: bf16 (Optimized balance between performance and memory efficiency)
• Main Trigger: The model is triggered by the phrase "a can of ..." 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

Specifically trained to generate a wide array of soda can images, this LoRA model can cater to creative, educational, and marketing needs.

Performance and Limitations

• Performance: Shows strong capability in rendering soda cans with varied designs and in different contexts.
• Limitations: Given the dataset size of 200 images, the model might exhibit limitations in generating highly unique can designs not represented in the training set.

Ethical Considerations

• Intended Use: Aimed at non-commercial applications, including creative design and educational projects.
• Bias and Fairness: Users should be cautious of potential dataset biases towards certain brands or can designs.

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

Feedback and contributions to enhance the model are encouraged. For suggestions or contributions to the model's development, please connect through the model's Hugging Face page.

Trigger words

Use `a can of "..."` to prompt the image generation process.

Download model

The model's weights are available in Safetensors format for download.

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.