A primitive(?) merge of furry model with the anime.<pre><code>fluffyrock-1088-zsnr-vpred-e255-minsnr-e29.safetensors / divineanimemix_V2.safetensors</code></pre><h3 id="heading-7887">Pros over furry model:</h3><ul><li>Better understanding of anime LoRA;</li><li>No fucked-up style no matter how many artists you put in;</li><li>Kinda no artifacts in shaded areas.</li></ul><h3 id="heading-7888">Pros over anime model:</h3><ul><li>Knows more concepts.</li></ul><h3 id="heading-7889">Minuses:</h3><ul><li>Anime character LoRAs seem to work worse than on anime models;</li><li>Mostly don't know anime model basic and acknowledgeable characters;</li><li>Character detailing with rear view may be worse than front.</li></ul><h1 id="heading-7890">Installation:</h1><ol><li>Download and put the model (.safetensors) and config file (.yaml) to the stable diffusion models folder. A configuration file is required for the model to run;</li><li>Download <a target="_blank" rel="ugc" href="https://github.com/Seshelle/CFG_Rescale_webui">CFGRescale</a> from webui addons;</li><li>Download the <a target="_blank" rel="ugc" href="https://cdn.discordapp.com/attachments/1076194351484510219/1170118455358390354/fluffyrock_3m.csv">tag file</a> and throw it in the path "extensions\a1111-sd-webui-tagcomplete\tags" and activate it in the settings (you must have <a target="_blank" rel="ugc" href="https://github.com/DominikDoom/a1111-sd-webui-tagcomplete">TagAutocomplete </a>extension);</li></ol><h3 id="heading-7891">Extra QoL's:</h3><ol><li>Download Embed and LoRA:<ol><li>Negative embedding <a target="_blank" rel="ugc" href="https://civarchive.com/models/87781?modelVersionId=94126">https://civarchive.com/models/87781?modelVersionId=94126</a>;</li><li>Quality tags LoRA <a target="_blank" rel="ugc" href="https://civarchive.com/models/127533/fluffyrock-quality-tags">https://civarchive.com/models/127533/fluffyrock-quality-tags</a>;</li></ol></li><li><a target="_blank" rel="ugc" href="https://github.com/ljleb/sd-webui-freeu">FreeU</a> - download in extensions (either by link or name):<ol><li>Start At Step - 0.1, Stop At Step - 0.45;</li><li>The difference between "Version" and "Recommendations" seems to be at the margin of error;</li></ol></li><li><a target="_blank" rel="ugc" href="https://github.com/ljleb/sd-webui-freeu">Wildcards</a> - download in extensions (either by link or by name), download the <a target="_blank" rel="ugc" href="https://cdn.discordapp.com/attachments/1127930990870933534/1129015287325401098/e6ta.zip">archive of cards</a> for the model and unpack it to "extensions\sd-dynamic-prompts\wildcards". Contains cards by tag names, in which the authors who drew artwork with those tags are laid out;</li><li><a target="_blank" rel="ugc" href="https://mega.nz/folder/OoYWzR6L#psN69wnC2ljJ9OQS2FDHoQ/folder/f44E2YjK">LoRAs</a> trained on furry models.</li></ol><h1 id="heading-7892">Generation tips:</h1><ol><li>Clip Skip 1;</li><li>CFG 6-10;</li><li>CFGRescale set to 0.6-0.7;</li><li>Render image size from 512 to 1088, but it is better not to set above 960 and not below 576;</li><li>In settings, set VAE encode and decode type to TAESD on both options, it will reduce overcooked look and prevent most of baked and burned out spots;</li><li>If you want humanoids - In the beginning of the prompt - "human, [not furry], your request", then add sex of the person: female or male or intersex, the latter is better to mix with female;</li><li>Add some artists to the request to get better result, example: by masha / by merunyaa / by cutesexyrobutts. You can find more artists <a target="_blank" rel="ugc" href="https://e621.net/posts?tags=date%3A..3months">here</a> (add tags that you are interested in).</li><li>Prompting is similar to the danbooru (anime), and easily convertible to e621 prompt by using tag autocompletion file.</li></ol>You can find more tips on the page of fluffyrock model - <a target="_blank" rel="ugc" href="https://civarchive.com/models/92450/fluffyrock">https://civarchive.com/models/92450/fluffyrock</a><hr />Huge thanks to <a target="_blank" rel="ugc" href="https://civarchive.com/user/WithoutOrdinary">WithoutOrdinary</a> for amazing and versatile <a target="_blank" rel="ugc" href="https://civarchive.com/models/95587/divineanimemix">model</a>!Huge thanks to <a target="_blank" rel="ugc" href="https://civarchive.com/user/TroubleDarkness">TroubleDarkness</a> for making <a target="_blank" rel="ugc" href="https://civarchive.com/models/95587/divineanimemix">anime-style model</a> that is capable of good prompt understanding and good compatibility with LoRAs!Another thanks to the torkroll from lodestone_rock's server for pointing out the merge recipe.<hr />Please leave a review and describe what can be improved if you find an opportunity, or tell me if there any unlisted flaws compared to pure fluffyrock/anime models.That can help others when reading this info.Thank you for reviewing this model!

Files with SHA256: 60703e062d68d79d8b7c651454827629d20de95f0562fa6f0295cb15f030c2df