blibla_style_lora_sdxl

Blibla Style LoRA SDXL

Captain: The AI platform that evolves to your needs

• 🚀 Check out Captain
• 👩‍💻 Captain on GitHub

<Gallery />

Model Description

This model is a sophisticated blend of weights from various ethically trained LoRAs. It combines the unique styles of different artists and caricature elements as well as photographs and textures, providing a diverse and powerful tool for generative tasks. The base models included in this merge are:

• Honore Daumier: Model Link
• Thomas Rowlandson: Model Link
• Caricature: Model Link
• Eugene Atget: Model Link
• Used Leather: Model Link

Additionally, we have incorporated preliminary weights from our research models that feature "Neon lights" and a "Photo" style LoRA trained on isolated items and special concepts. These models have been trained with the same ethical guidelines and are intended for non-commercial use upon release. All images used in training were sourced from Unsplash.

Merging Process

The merging process involved combining several models with varying weights on the Stable Diffusion XL (SDXL) architecture. From this, we extracted a LoRA with Network Rank 256 and Network Alpha 256, yielding highly effective results in style and detail fidelity. We then added our latest photography LoRA to get more versatility.

blibla_styles_merge:

• eugene_atget_sdxl_v1: 0.3
• honore_daumier_sdxl_v1: 0.3
• caricature_sdxl_v2: 0.3
• thomas_rowlandson_sdxl_v1: 0.3
• neon_light_sdxl_v1: 0.3
• used_leather_sdxl_v1: 0.3

blibla_styles_v2:

• photo_sdxl_v1-000010: 0.7
• blibla_styles_extracted: 0.6

Trigger Words

We added several triggers, like: lithography, caricature, nostalgic, handcolored etching, exaggerated, neon, used leather, weathered, visible stitching

Versatility in Styles

In addition to the caricature lithography style, this model is also capable of generating other artistic styles with high fidelity. For example:

• Hyperrealistic Cartoon: "A hyperrealistic cartoon of a {subject}, highres digital art, 4k resolution."
• Surrealistic Art: "A surrealistic painting of a {subject}, dream-like imagery, highres digital art, 4k resolution."
• Vintage Poster: "A vintage poster of a {subject}, retro style, bold colors, highres digital art, 4k resolution."
• Fantasy Illustration: "A fantasy illustration of a {subject}, magical elements, vibrant colors, highres digital art, 4k resolution."
• Minimalist Sketch: "A minimalist sketch of a {subject}, clean lines, monochrome, highres digital art, 4k resolution."

Sample Images

The sample images provided are designed to showcase the model's capabilities in rendering caricature lithographs of cartoon characters with exaggerated facial features, parodies of various historical and cultural figures as high-resolution digital art that mimics the nostalgic hand-colored etching style.

These images are an homage to meaningful but deceased personalities, offering a unique artistic perspective while adhering to ethical AI practices. Each image has been crafted to reflect the distinct characteristics of the personalities being parodied, demonstrating the model's ability to blend artistic styles and historical references seamlessly.

Intended Use

This model is designed for use in academic research and creative projects where ethical AI practices are upheld. It is ideal for those looking to explore artistic synthesis and generative art, especially in settings that respect and recognize the contributions of artists and AI ethics.

Ethical Considerations

All base models used in this merger have been developed under strict ethical guidelines, with an emphasis on reducing bias and respecting artistic integrity.

ℹ️ Dataset Information: The datasets used to train the base models are available for review and use. Detailed information and access to these datasets can be found on the individual model pages of each base LoRA linked above.

Limitations

While the model performs robustly across a variety of artistic styles, it may not perfectly emulate the nuances of each base model’s training data. Users are encouraged to experiment with different settings and provide feedback for future improvements.

Licensing

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

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.