README.md

---
pipeline_tag: text-to-image
widget:
- text: >-
    movie scene screencap, cinematic footage. thanos smelling a little yellow
    rose. extreme wide angle,
  output:
    url: 1man.png
- text: 'A tiny robot taking a break under a tree in the garden '
  output:
    url: robot.png
- text: mystery
  output:
    url: mystery.png
- text: a cat wearing sunglasses in the summer
  output:
    url: cat.png
- text: 'robot holding a sign that says ’a storm is coming’ '
  output:
    url: storm.png
- text: The Exegenesis of the soul, captured within a boundless well of starlight, pulsating and vibrating wisps, chiaroscuro, humming transformer
  output:
    url: soul.png
- text: >-
    Lady of War, chique dark clothes, vinyl, imposing pose, anime style, 90s
    natural photography of a man, glasses, cinematic,
  output:
    url: anime.png
- text: natural photography of a man, glasses, cinematic,  
  output:
    url: glasses.png  
- text: if I could turn back time
  output:
    url: time.png
- text: god
  output:
    url: god.png
---
<Gallery />

# Mobius: Redefining State-of-the-Art in Debiased Diffusion Models

Mobius, a revolutionary diffusion model, pushes the boundaries of domain-agnostic debiasing and representation realignment. By employing the cutting-edge constructive deconstruction framework, Mobius achieves unrivaled generalization across a vast array of styles and domains, eliminating the need for expensive pretraining from scratch.

# Domain-Agnostic Debiasing: A Groundbreaking Approach

Domain-agnostic debiasing is a novel technique pioneered Corcel. This innovative approach aims to remove biases inherent in diffusion models without limiting their ability to generalize across diverse domains. Traditional debiasing methods often focus on specific domains or styles, resulting in models that struggle to adapt to new or unseen contexts. In contrast, domain-agnostic debiasing ensures that the model remains unbiased while maintaining its versatility and adaptability.

The key to domain-agnostic debiasing lies in the constructive deconstruction framework, a proprietary method developed by the Corcel Diffusion team. This framework allows for fine-grained reworking of biases and representations without the need for pretraining from scratch. The technical details of this groundbreaking approach will be discussed in an upcoming research paper, "Constructive Deconstruction: Domain-Agnostic Debiasing of Diffusion Models," which will be made available on the Corcel.io website and through scientific publications.

By applying domain-agnostic debiasing, Mobius sets a new standard for fairness and impartiality in image generation while maintaining its exceptional ability to adapt to a wide range of styles and domains.

# Surpassing the State-of-the-Art

Mobius outperforms existing state-of-the-art diffusion models in several key areas:

Unbiased generation: Mobius generates images that are virtually free from the inherent biases commonly found in other diffusion models, setting a new benchmark for fairness and impartiality across all domains.

Exceptional generalization: With its unparalleled ability to adapt to an extensive range of styles and domains, Mobius consistently delivers top-quality results, surpassing the limitations of previous models.

Efficient fine-tuning: The Mobius base model serves as a superior foundation for creating specialized models tailored to specific tasks or domains, requiring significantly less fine-tuning and computational resources compared to other state-of-the-art models.


## Usage and Recommendations

- a CFG of either 3.5 to 6.5
- Requires a CLIP skip of -3
- highly suggested to preappenmed watermark to all negatives and keep negatives simple such as "watermark" or "worst, watermark"

## License

Mobius is released under a custom license that governs its usage and distribution rights:

Non-commercial use: The model is fully open and available for any non-commercial use. Researchers, students, and enthusiasts are encouraged to explore, modify, and build upon the model freely, as long as they do not use it for commercial purposes.

Commercial use on the Bittensor network: For commercial applications, the model is exclusively available through the Bittensor network. This allows Corcel to generate revenue and support the ongoing development and maintenance of the model. Any commercial use outside of the Bittensor network is strictly prohibited.

Commercial use for entities with revenue below $100,000 USD: Entities with an annual revenue below $100,000 USD can use the model commercially without going through the Bittensor network. This provision aims to support small businesses and startups while still maintaining the model's accessibility. However, these entities must obtain written permission from Corcel before using the model commercially.

Redistribution: The model cannot be redistributed by any accounts or entities not directly associated with Corcel. This includes sharing the model weights, code, or any other materials related to the model.

Derivatives: Any derivatives or modifications of the model must retain the "Mobius" name as part of their name or identifier. For example, a derivative model focused on anime-style images must be named "MobiusAnimeXL" or similar. This ensures that the original Mobius model is acknowledged and credited for its contributions.

Ownership of generated images: Images generated using the Mobius model belong to the individual or entity that provided the prompt for the image generation. Corcel claims no ownership or rights over the generated images.

By using the Mobius model, you agree to comply with the terms and conditions outlined in this license. Corcel reserves the right to update or modify this license at any time without prior notice.