<h2 id="reminder-you-can-use-the-styles-in-this-checkpoint-without-score-tags-and-up-to-cfg-8!hi-there!-welcome-to-a-v.1.1-of-my-very-amateurish-finetune-on-pdv6-aimed-at-having-some-working-artist-styles-without-going-crazy-or-training-over-existing-knowledge-(-for-example-fumihiko-and-cutesexyrobutts)-with-some-custom-tokens-so-the-styles-can-get-trained-from-scratch-this-has-uh-245-()-ish-styles-working-some-might-be-underbaked-and-should-be-fixed-in-later-finetunes-as-the-idea-is-to-keep-adding-styles-overtime-(this-will-include-pdv6.9-or-7-whenever-that-drops)-also-wasn't-able-to-generate-samples-for-all-artists-styles-but-all-triggers-in-the-txt-file-below-do-work-tee-hee-pero~~-fdw1yg9x0">Reminder, you can use the styles in this checkpoint without Score tags, and up to cfg 8! Hi there! Welcome to a v.1.1 of my very amateurish finetune on PDv6 aimed at having some working artist styles without going crazy or training over existing knowledge ( for example fumihiko and cutesexyrobutts) with some custom tokens so the styles can get trained from scratch, this has uh 245 (?) ish styles working, some might be underbaked, and should be fixed in later finetunes as the idea is to keep adding styles overtime (this will include PDv6.9 or 7 whenever that drops), also wasn't able to generate samples for all artists styles but all triggers in the txt file below do work tee-hee-pero~~</h2>Artist tokens work best before the score tags, do keep in mind this, some artists tokens may collide with some activation tokens for other LoRAs/DoRAs due to PDv6 reasons, You can find the list of artists <a target="_blank" rel="ugc" href="https://docs.google.com/spreadsheets/d/1EI3eT2Fl6Q-NO2oQtZ-Enw6g4bpmaC3VTC-UjSzBcNQ/edit?gid=0#gid=0">here</a>(updating), and just the list of triggers <a target="_blank" rel="ugc" href="https://files.catbox.moe/3taf0o.txt">here</a>, style mixing works just have to play with weights, also you can put them in negatives to further guide how you want it to look. Emphasis mode No Norm is suggested for SDXL models.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/188aa7da-be38-414c-8a96-63dd33708043/width=525/188aa7da-be38-414c-8a96-63dd33708043.jpeg" />Huge thanks to @Anzhc with his help in training hyperparameters, to @FallenIncursio , @mfcg, @mnemosynekotorin , @richyrich515 , @justTNP, and @Kojimbomber they were kind enough to provide much needed data for this! If you want bigger girls go and use mnemosynekotorin's <a target="_blank" rel="ugc" href="https://civarchive.com/models/561122/venus-body-or-ponyxl?modelVersionId=624971">Venus Body</a> lora Positive prompt : score_9, score_7_up Helper prompts : score_8_up for photorealistic shading (Zumi, eu03() adviced but not needed, source_anime to make it closer to animeNegative prompt : monochrome, 3d (when not desired), username, watermark, signaturePersonal schizo Negative prompt: worst quality, low quality, simple background, white background, sketch, normal quality, jpeg artifacts, depth of field, blurry, bloom, messy drawing, amateur drawing, fewer digits, extra digits, source_pony, source_furry, source_cartoon, signature, watermark, username, 3d, monochromeSampler : Euler A AYS, Any Align Your Steps even GITS.CFG : 4 to 7 (can be pushed up to 9 and it will work on a lot of promptsIf you want to support me, consider liking the model, and/or tipping buzz/donating to my <a target="_blank" rel="ugc" href="https://ko-fi.com/bluvoll">Ko-fi</a>, as this was finetuned on 8xA100 (damn this v1.1 was even more expensive)

Files with SHA256: c2cad39bea4848450c1bf5d94d18f448131ebd9747701219163fbd01bc7bd507