DESSEP "SDXL-v1"(a4) Model Card

This model card focuses on the model associated with the Stable Diffusion XL v1.0 model, codebase available here.

Model Details

• Developed by: Stability AI
• Model type: Diffusion-based text-to-image generation model
• Language(s): English
• License: CreativeML Open RAIL++-M License
• Model Description: This is a model that can be used to generate and modify images based on text prompts.

Malicious Use, and Out-of-Scope Use

• You can use this model for both commercial and non-commercial purposes.
• You have the right to improve, modify, and use this model within the limits specified in this license.

The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.

Out-of-Scope Use

The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.

Misuse and Malicious Use

Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:

• Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
• Intentionally promoting or propagating discriminatory content or harmful stereotypes.
• Impersonating individuals without their consent.
• Sexual content without consent of the people who might see it.
• Mis- and disinformation
• Representations of egregious violence and gore
• Sharing of copyrighted or licensed material in violation of its terms of use.
• Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.

Limitations

• The model cannot render legible text
• The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
• Faces and people in general may not be generated properly.
• The model was trained mainly with English captions and will not work as well in other languages.
• The autoencoding part of the model is lossy

Training

Training Data This version is based on stable-diffusion-xl-base-1.0 and has undergone minor fine-tuning on 80 specially selected images. The current name of the version is "a4". This version will serve as a starting point for subsequent training of my models based on SDXL. (OpenCLIP-ViT/G and CLIP-ViT/L) have not been changed.

*Training steps are not the number of image repetitions during the model training process. The number of image repetitions is not indicated in the plan.

Addition

The model's capabilities can be expanded using: LoRa, LyCORIS, HyperNetwork

NOTE

Any financial support, even a small one, will help speed up the model’s training process.

• ETH: 0xD07C4bB4F8470dFA3B85dD972f9171B932Fcb165
• BTC: 1iCZHQrmtodDcEjnhUpakBi9y7voRjzjs

*This model card was written by: Evgeniy Pantin