<p>Please give revies and comments then I can make the model better.</p><h1 id="please-read-description-for-a-guide-+-how-to-prompt-for-best-images-agoegee3k">PLEASE READ DESCRIPTION FOR A GUIDE + how to prompt, for best images</h1><h2 id="what-model-should-i-choose-towbab3a0">WHAT MODEL SHOULD I CHOOSE?</h2><p>Vanilla: Kinda ok, OK SFW and NSFW</p><p>Sakura: good, good SFW and NSFW</p><p>Niji models: Pretty good, Pretty good SFW, Ok NSFW</p><p>Pear: Very good, Very good SFW and NSFW</p><p>Fused: Really good, good Lora and Lycoris support, Really good SFW and NSFW</p><p>Lemon Version A: Excellent, BAD LORA AND LYCORIS SUPPORT, pretty good SFW and NSFW</p><p>Lemon Version B: Excellent, Good Lora/Lycoris support trained on Nai or Anylora Great Lora/Lycoris support trained on fluffyrock, Excellent SFW and NSFW</p><p>Grapefruit: Seems to have the best so far SFW and NSFW (OUT OF DATE: only for previous models), Seems to be great with Loras trained on fluffyrock and the NAI leak/Anime_full</p><p>Clementine: has better style, versatility and NSFW compared to the last few models Plus, I'm using new base prompts for the best results, You can expect this model Very soon.</p><p>REBOOTED: The model which has tooken the place of all previous models. it has a few kinks, but when I add VPRED to it it should become better...</p><p><a target="_blank" rel="ugc" href="https://files.catbox.moe/oeax9f.gif">https://files.catbox.moe/oeax9f.gif</a></p><h3 id="boring-random-notes:-l79tpjxdo">Boring RANDOM notes:</h3><p>A continuation of my other model- <a target="_blank" rel="ugc" href="https://civarchive.com/models/43887/crosslawlasmix">CrossLawlasMix</a>, but with more models mixed in selectively to make sure it would be the best quality AND I would be able to set the permissions to what I thought would be good. Also wanna find more of my models? Go here: <a target="_blank" rel="ugc" href="https://huggingface.co/Masterjp123/Masterjps-Models">HuggingFace,</a> <a target="_blank" rel="ugc" href="https://civarchive.com/user/Masterjp123">My-Profile</a>.</p><p>NOTE: My HuggingFace does have more models that are not published here but most are experimental SO their names maybe misleading. Also I work on LLM stuff there mainly LLAMA models because they are easy to quantize when I can. Also I have been having troubles uploading files to hugging face so I guess no uploading for now :'(</p><p>VANILLA IS THE FIRST <u>STYLE/VERSION</u> meaning the next models MAY or MAY NOT improve on quality.</p><p>I Do encourage people to upload my models to other websites, the only thing I ask is that you link back to here.</p><p>Also Vpred models will have VPD or just VPRED in their name.</p><p>All of the images were created using <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a></p><p>Here is the HuggingFace Repo -&gt; <a target="_blank" rel="ugc" href="https://huggingface.co/Masterjp123/Random-Model-Storage">Here</a>! &lt;-</p><h1 id="documentation-on-model-(how-to-use-the-model)-3n39ho3jc">DOCUMENTATION ON MODEL (how to use the Model)</h1><h2 id="section-1-prompting:-pa3n626o9">SECTION #1 Prompting:</h2><p>Prompting for this model is quite versatile but using e621 tags will give you better results and using the negative and positive prompts here, Also UPDATE: The model supports Artist tags now!!! Yiffy mix tags to be specific.</p><pre><code>(masterpiece, highest quality, 16k, high quality, best quality:1.3, highres, digital painting \(artwork\), furry, uploaded_on_e621:1.4), absurd res, RAW photo, (by zackary911, by canson, by theawesomefoxguy), by null-ghost, by s1m, (sharp focus:1), ((cel shading)), (realistic, kemono), BREAK

[PUT E621TAGS YOU WANT HERE]</code></pre><p>And For the Negative prompt I recommend this:</p><pre><code>low res, lowres, blurry, bad anatomy, letterbox, deformity, mutilated, malformed, amputee, watermark, signature, unusual anatomy, username, sketch, monochrome, (worst quality:2),(low quality:2),(normal quality:2),((monochrome)),((grayscale)),watermark, blurred, bad face, old, (cub:1.2, child:1.2, young:1.2),bad anatomy,(long body :1.3), BadDream, badyiffymix41, boring_e621_fluffyrock_v4, boring_e621_v4, easynegative, EasyNegativeV2, FastNegativeV2, fluffynegative, negative_hand-neg, ng_deepnegative_v1_75t, NGH, SimpleNegativeV3, updn, &lt;lora:neg4all_bdsqlsz_V3.5:1&gt;</code></pre><p>Also Ps, you are going to need the negative embeddings, unless you want bad results.</p><p>I have also put all the embeds and Loras in the following link so you guys don't have to get them yourself: <a target="_blank" rel="ugc" href="https://mega.nz/folder/8y0mFRBT#r2SaP2k-Gm__30AX74JhwQ">https://mega.nz/folder/8y0mFRBT#r2SaP2k-Gm__30AX74JhwQ</a></p><h2 id="section-2-generation-settings:-r7vflbwu5">SECTION #2 Generation settings:</h2><p>Higher Steps = better image</p><p>Lower CFG = more creative BUT more inaccurate</p><p>I suggest you use:</p><pre><code>Steps: 40+ for best results, Sampler: DPM++ 2M SDE Heun Karras but DPM++ 2M Karras also works, CFG scale: 10</code></pre><p>but if you want you can use:</p><pre><code>Steps: 20-28 , Sampler: Euler a, CFG scale: 7</code></pre><h2 id="section-3-upscaling:-y2lbuf6rj">SECTION #3 Upscaling:</h2><pre><code>Upscaler: R-ESRGAN 4x+ Anime6B (Or really any anime style upscaler), Denoising strength: 0.3, </code></pre>

Furation

<p>An improve ment on Vanilla and ment to do more of an anime style, HEAVILY UNTESTED SO IT's CAPIBLITES ARE UNKNOWN TO ME. Also baked in Vae.</p>

Files with SHA256: 0f0d1eda785526a5de8a9b1be1181684d5161aa66db5447d46af61ee42197c34