(Yes I'm mimicking how WarriorMama777 doing this page. But I don't really know how, and I'm too lazy to learn this)
↓Licence 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:
You can't use the model to deliberately produce nor share illegal or harmful outputs or content 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 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 Terms of use Clearly indicate where modifications have been made. If you used it for merging, please state what steps you took to do so.
↓Disclaimer READ MORE: Disclaimer The user has complete control over whether or not to generate NSFW content, and the user's decision to enjoy either SFW or NSFW is entirely up to the user.The learning model does not contain any obscene visual content that can be viewed with a single click.The posting of the Learning Model is not intended to display obscene material in a public place. In publishing examples of the generation of copyrighted characters, I consider the following cases to be exceptional cases in which unauthorised use is permitted. "when the use is for private use or research purposes; when the work is used as material for merchandising (however, this does not apply when the main use of the work is to be merchandised); when the work is used in criticism, commentary or news reporting; when the work is used as a parody or derivative work to demonstrate originality." In these cases, use against the will of the copyright holder or use for unjustified gain should still be avoided, and if a complaint is lodged by the copyright holder, it is guaranteed that the publication will be stopped as soon as possible. I would also like to note that I am aware of the fact that many of the merged models use NAI, which is learned from Danbooru and other sites that could be interpreted as illegal, and whose model data itself is also a leak, and that this should be watched carefully. I believe that the best we can do is to expand the possibilities of GenerativeAI while protecting the works of illustrators and artists.
↓About
The main model, “NSX-1（NotSoXJBMix-1)”, is a merged model that generates high quality anime style pictures. This model can generate a wide variety of content. Hope this model can help you visualize your imagination.
“Hope everyone can visualize their imagination。”
↓NSX1 Features：High quality，anime illustration style。
1.Normally won’t generate NSFW pictures. 。
2.Fully support of NSFW generation.
In addition, thanks to excellent extensions such asModelToolkit”https://github.com/arenatemp/stable-diffusion-webui-model-toolkit“ （Otherwise this model could be 5~6GB）。
↓Variations
NSX1A
Features ：More flat style. I like to apply anime character LoRA with this.
NSX1B
Features ：More coloful, more pastel style.
NSX1C
Features ：More realistic light and shadow, more realistic texture. Close to AOM3
NSX1D
Features : Added pastel-mix. A plus version of NSX1B.
NSX1Night
Features ： More nsfw atmosphere
NSX1EzBackground
Features: Can generate a illustration with background even if you are bad at prompting background prompts. More
When generating illustrations for the general public: write "nsfw" in the negative prompt field When generating adult illustrations: "nsfw" in the positive prompt field -> It can be generated without putting it in. If you include it, the atmosphere will be more NSFW.
↓Gallery
More examples:https://civitai.com/models/28200/notsoxjbmix-1
↓How to use Prompts I’m using EasyNegative and badhandsv4 for negative prompts.(or just use”(worst quality, low quality:1.4)”） How to avoid Bokeh (depth of field, bokeh, blurry:1.4) How to remove mosaic:(censored, mosaic censoring, bar censor, convenient censoring, pointless censoring:1.0) How to remove blush:(blush, embarrassed, nose blush, light blush, full-face blush:1.4) How to remove NSFW effects:(trembling, motion lines, motion blur, emphasis lines:1.2)
Sampler：Pick your own choice Steps：(Not too high） DPM++ SDE Karras: 20 to 40 DPM++ 2M Karras: 28 to 40 Eular A:30 to 50 Clipskip: 1 or 2 CFG: 6 to 12 Upscaler: Detailed illust：Latenet(nearest-exact)/RealESRGAN_4xplus_anime_6B Denoise strength：0.5~0.6
Simple upscale：Whatever
Model details / Recipe
↓New Hash(short) NSX-1.safetensors 8ee9ff7d94 NSX-1A-purned.safetensors 5c9f713a34 NSX-1B-purned.safetensors 536eab3410 NSX-1C-purned.safetensors ba9f4f9007 NSX-1D-purned.safetensors c0edebdde7 NotSoXJB-1Night-purned.safetensors e4c8f27226
↓Use Models (new short Hash）
1.AOM3A1B.safetensors [5493a0ec49]
2.Counterfeit-V2.5_pruned.safetensors [a074b8864e]
3.viewerMixV17_viewerMixV17V2.safetensors [c47e3a94e9]
4.nyanMix_230303Absurd2.safetensors [8ac3e79e96]
5.nightSkyYOZORAStyle_yozoraV1PurnedFp16.safetensors [4b118b2d1b]
6.colorBoxModel_colorBOX.safetensors [93a20525f5]
7.9527_v10.ckpt [40a9f4ec37]
8.furnace34_furnace34.safetensors [c0653dd6d0]
9.pastelmix.safetensors [fa818fcf2c]
10.AOM3_aom3a3.safetensors [eb4099ba9c]
11.hassakuHentaiModel_hassakuv1.safetensors [df614cd3c2]
↓NSX1
Step1：
Step2：
Step3：
Step4：
Step5：
Step6：
↓NSX1A
↓NSX1B NotSoXJB + (9527_v10-NotSoXJB-1) - 0.45 Add difference
↓NSX1C NotSoXJB-1 + (AOM3-NotSoXJB-1) - 0.6 Add difference
↓NSX1D
↓NSX1Night NotSoXJB + (hassakuHentaiModel-NotSoXJB-1) - 0.45 Add difference
↓NSX1EzBackground NotSoXJB + (CounterfeitV2.5-pruned-NotSoXJB-1) - 0.3 Add difference