05-11-25<h1 id="popskull-2.0-rctxtks2c">PopSkull 2.0</h1>try it without a negative for best results on getting finer artistic details04.17.25--1.9 Final Uploaded. Previous version taken down.artists added:Francis Bacon(updated)Troy Brooks(updated)Wes Benscoter(updated)Andrew SalgadoAndrew WyethChaim SoutineFrank AuerbachGene DavisJames RosenquistJim MahfoodJohn Pitreknox martinMartine JohannaNicolai FechinMatt SesowPaul JenkinsPaul RumseyPhilip PearlsteinRashid JohnsonTom Lovell 03.29.25–<h2 id="1.8-final-uploaded.-c1k3savjz">1.8 Final uploaded.</h2>Artists added:Arthur MelvilleCharles WhiteChris LeibDavid BowersDavid BromleyDiego DayerEric FischlErik JonesFriedel DzubasJocelyn HobbieJulian_Schnabel(fix syntax in next release)Karel AppelNorman BluhmRuss MillsShozo ShimamotoTodd JamesTuen HocksYonatan Frimer<h3 id="03.17.25-al4c9lyv2">03.17.25--</h3><h3 id="uploaded-replacement-model-for-1.8-0jsbcfdxy">uploaded replacement model for 1.8</h3>if you already downloaded the previous upload of this version, it's a good all-around model and may be the basis for the next DJ Ranch MixUse BB5 negative for now. 1.8 is beta testing. i may take it down and replace with another.prompting suggestion: (Harvey Dunn, Sam Guay, oilpainting, traditional media, 1girl, ),...(Adolph Gottlieb, Wu Guanzhong, Boris Grigoriev, oilpainting, abstract, 1girl,)...(Michael Hussar, Troy Brooks, Todd Schorr, Ray Caesar, Greg Simkins, oilpainting, lowbrow, 1girl)...Some artist's influence is light. You may need to (Peter Max:1.4)Artist styles:Adolph GottliebAlbert GoodwinAlex GarantAlex GrossArnold BocklinBeauford DelaneyBoris GrigorievBrent CottonClive BarkerCraolaErnst FuchsFrancis BaconFrancisco GoyaFred CalleriGreg SimkinsH. A. BrendekildeHarvey DunnHasui KawaseHenry DargerHieronymus BoschHonore DaumierHope GangloffIrma SternJames DietzJean DuBuffetJean FouquetJean-Louis ForainJean-Michel BasquiatJeff ChristensenJimmy MarbleJoan EardleyJohn Anster FitzgeraldJohn BratbyJose Clemente OrozcoJosh AdamskiJunji ItoJustin GaffreyKim Jung GiLeonardo DavinciLeonora CarringtonLucien FreudLucy GrossmithLuke ChuehMargaret Macdonald MackintoshMarianne NorthMarianne von WerefkinMark DemsteaderMati KlarweinMaud LewisMax BeckmannMichael CarsonMichael ChevalMichael HussarMichael ParkesMikalojus Konstantinas CiurlionisNicolas DelortNicole EisenmanNina Chanel AbneyNoriyoshi OhraiOdd NerdrumPaul CaddenPaul CadmusPeter DoigPeter MaxPhilip GustonPJ CrookRay CaesarRemedios VaroRobert ColeScottSalvador DaliSam GuaySanford robinson giffordSatoru TakizawaSigmar PolkeSqueak CarnwathStanley DonwoodTatsuro KiuchiThomas DewingTodd SchorrTomasz Alen KoperaTroy BrooksVictor BraunerVictor MoscosoVirgil FinlayWes BenscoterWilliam Merritt ChaseWu Guanzhong<hr /><hr /><hr /><hr /><hr />Why haven't i updated the model or gone for a newer flexable model? cost. if you want me to train more i need more buzz. not asking for money. but if you have buzz then it makes it easier for me to train.<h2 id="recommended-settings-tx26aidfc">Recommended settings</h2><ol><li>Steps: 20,</li><li>Sampler: DPM++ 2M Karras,</li><li>Guidance Scale: 5.0,</li><li>Size:512x768 then upscale</li><li>Clipskip: I can’t decide</li><li>1: more saturated, follows the prompts a bit better</li><li>Tends to look a bit too clean sometimes</li><li>2. More desaturated, follows danbooru tagging a bit better, has an older comic feel to it, also a few more styles come through better in the mix with this.</li><li></li></ol>1.7 new artist styles added.Hasui KawaseIrma SternJosh AdamskiMarianne NorthMati KlarweinMaud LewisMarianne von WerefkinMax BeckmannMichael ParkesMikalojus Konstantinas CiurlionisNicolas DelortRemedios VaroStanley DonwoodTomasz Alen KoperaTatsuro KiuchiVictor BraunerVictor MoscosoVirgil FinlayPhilip GustonMargaret Macdonald MackintoshNoriyoshi OhraiPeter Max(simple 1 click vote to Tell me which checkpoint suits your needs the best so i know which one to merge back in on further expansions)<a target="_blank" rel="ugc" href="https://www.surveymonkey.com/r/D5W5HKG">here</a>if the survey doesnt work let me know via chat, ill try to figure out a way to show the results here. im not trying to market anything, just thought it would be nice to know what people thought.1.6 - info to come, seems clip skip 2 is working better with this update, trained in some midjourney painter and cartoonist sample images, as well as some some artist specific loras that I trained. will try to document more later.If you like the model and want to give a cup of coffee, you can do that <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/djnastymag2">here.</a>1.1- gave it a realistic burnout by laying in epicCartoon underneath like a low pile carpet, no offensive to it, but used to get rid of a lot of the realism left over from my trained model that I lora'd on top of. epicCartoon gets super big props for this as it should have been the model that this was built off of but I didn't know it existed. It doesn't change most of the model but helps with further training.0.95cleaned a lot, which unfortunately removed most of the trained data but hopefully will be worth it when retraining on this version, will post again hopefully its the v1.0you may see "Chode***" in the prompts of the some of the sample images because that was the original name of what the PopSkull model was going to be called CHODE an acronym for Curated Hauntings of Divergent Expressions. ;)****something something letters symbols thingsPOPSKULL 0.5 BETA0.85 may be a bit too heavy on the grime. I feel like I maybe have lost some of the fun. let me know.SURREALDARK FANTASYLOWBROWLOWBROW ARTPOSSIBLE COLLAGEARTISTSHORRORPOSTMODERNISMPOP SURREALISMPOPARTKITSCH**Antiquated, only applies to the first of the betas***I’ve added a helpful negative embedding for this model as a zip file. It’s listed as a checkpoint because there wasn’t another option. It’s only a 5 vector TI so it shouldn’t weigh down the negative too much.try including words like lowbrow, pop surrealism, and artists that you like

PopSkull

cleaned a lot, which unforunately removed 5 of the trained data but hopefully will be worth it when retraining on this version, will post v1.0 soon. Mostly ran negative loras on this, no new material added.

Files with SHA256: c04e9b1884d59ae6829b037cf32e6440fd786b38f2cc86a22efe57ca4974311f