Commit Safetensors model and READMEN.md

OpenNiji-V2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1423c9c9ce931235f4a4adb3d10da3cdb5d012f391145ff4524de7544bba90cf
+size 2132625640

README.md

@@ -1,3 +1,54 @@
----
-license: creativeml-openrail-m
----
+
+![Logo](https://i.imgur.com/cZMzjI6.png)
+
+
+# OpenNiji-V2
+The **NEW** Stable Diffusion model trained on **180k** Nijijourney images!
+
+
+
+
+
+## Acknowledgements
+
+ - [SD-Silicon - Xynon](https://huggingface.co/Xynon/SD-Silicon)
+ - [Nijijourney - Spellbrush](https://nijijourney.com/en/)
+ - [Kohya Trainer - bmaltais](https://github.com/bmaltais/kohya_ss)
+ 
+
+
+## Results
+
+![Result](https://i.imgur.com/dDR1tRn.png)
+```
+1girl, eyes closed, slight smile, underwater, water bubbles, reflection, long light brown hair, bloom, depth of field, bokeh
+```
+![Result](https://i.imgur.com/B5HtiVz.png)
+```
+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
+```
+![Result](https://i.imgur.com/GwEagun.png)
+```
+1girl, looking at viewer, (highly detailed), (realistic), reflections (transparent) iridescent opaque jacket, long transparent iridescent hair, bloom, depth of field, bokeh, cinematic lighting, dynamic pose, (full body), ((ultra realistic perfect face))
+```
+
+## Dataset
+
+Due to the size of the dataset (and how it was scraped) there are quite a few broken images and images without prompts, we plan to resolve these issues and release the dataset eventually. The dataset is 196 GB in size and took 1 night of scraping all the nijijourney image generation channels.
+
+## Small Note
+
+This model already has the in01 trick applied, so this model should be better at generating hands! 
+- (This is not going to work 100% of the time, and manual hand fixes may be required)
+
+
+## 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](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
+