Openniji

🚀 OpenNiji

The Stable Diffusion model trained on Nijijourney images!

🚀 Quick Start

The project involves a Stable Diffusion model trained on Nijijourney images. It offers different versions and datasets, and has various features and usage scenarios.

✨ Features

• New Version Release: OpenNiji-V2 is now available here.
• Dataset Update: V3 of the dataset is released here. Although it's not the training dataset, it includes the relevant images and has higher quality thanks to NijiJourney V5.
• LoRA Version: Added the LoRA version of finetune, enabling OpenNiji to be used on any model.
• Hand Generation: The model has the in01 trick applied, making it better at generating hands.

📚 Documentation

Announcements

• OpenNiji-V2 is Out Now!
• V3 of the dataset released Here
  • This is NOT the dataset we trained on, however, it still includes those images, and is overall a higher quality dataset thanks to NijiJourney V5!

Changelog

• Added LoRA version of finetune, you should now be able to use OpenNiji on any model!

Acknowledgements

• Anythingv4.5 - Andite
• Nijijourney - Spellbrush
• Kohya Trainer - bmaltais

Results

1girl, eyes closed, slight smile, underwater, water bubbles, reflection, long light brown hair, bloom, depth of field, bokeh

masterpiece, best quality, 1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewellery, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt

Small Note

This model already has the in01 trick applied, so this model should be better at generating hands!

📄 License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here