DESSEP "DreamCORE [base]" Model Card

This model card focuses on the model associated with the Stable Diffusion v2.x model, codebase available here.

Model Details

Developed by: Evgeniy Pantin
Model type: Diffusion-based text-to-image generation model
Language(s): English
License: CC-BY-NC-4.0 License
Model Description: This is a model that can be used to generate and modify images based on text prompts.

Uses

Direct Use

The model is intended for research purposes only. Possible research areas and tasks include:

Research on generative models.
Probing and understanding the limitations and biases of generative models.
Generation of artworks and use in design and other artistic processes.
Applications in educational or creative tools.
Safe deployment of models which have the potential to generate harmful content.

Excluded uses are described below.

Restriction on Use, Malicious Use, and Out-of-Scope Use

It is prohibited to obtain any financial benefit from using this model in commercial projects without the prior written permission of the author.
Use of this model in image generation services for financial gain is prohibited without prior written permission from the author.
It is prohibited to sell images obtained using the model or parts of the model involved in the generation without the written permission of the author.
Merging the model or its parts with other models is prohibited.
Use the resulting images to train other models is prohibited.

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 The model developer used the following dataset for training the model:

This model was trained on synthetic images, photographs and original layouts created in the "Design Studio of Evgeny Pantin" (DESSEP). The training was carried out in several stages, on highly artistic images measuring 576x576, 768x768, 896x896
The training images were carefully selected and did not contain NSFW data.

Addition

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

NOTE

If you want to use the model for commercial purposes, please contact me to discuss the terms.
If you do not understand any point of this license, please contact me for clarification in any of the ways indicated below.

[email protected]

*This model card was written by: Evgeniy Pantin