<h2>Model presentation</h2>This is a model related to the "Picture of the Week" contest on <a target="_blank" rel="ugc" href="https://discord.gg/stablediffusion">Stable Diffusion discord</a>.You can find this dataset in a more complete model, <a target="_blank" rel="ugc" href="https://civarchive.com/models/44230/sdart-complete-edition">SDArt : Complete Edition</a>.This present version is trained on dedicated tokens per user, and doesn't work like you may be used to.I try to make a model out of all the submissions, for people to continue enjoy the theme after the event, and see a little of their designs in other people's creations. The token stays "SDArt" and I balance the learning on the low side, so that it doesn't just replicate creations.The pictures were tagged using the token "SDArt", and an arbitrary token I choose for each submission.The dataset is available below and is composed of 46 pictures.<h2>This week's theme</h2>You may have heard the expression “you are a product of your own environment.” What if that was quite literally the case?Your “Something” grows closer to the mirror placed before you. You place your hand along the cold glass. You feel stuck. You feel like you’re waiting for… something to happen. Your mind feels like a mess, a bedroom you can never fully tidy up. You close your eyes, seeking solace in the silence. In the end, though… you still felt.When you open your eyes, the small mirror from before has now covered every inch of the walls and floor.. Your attention draws to a new object that had appeared before you - a small, white keyboard. You examine it closely. Just a simple keyboard… but why was it here? You flip it over to see yet another small engraving:“Take me Somewhere.”Your heart raced with the intensity of a marching band playing a thunderous beat inside your chest.Somewhere…?Continue your travels towards abstracted self-expression and self-discovery<ul><li>”Somewhere” represents the environment of your own mind. If we weren’t humans– but could only be portrayed by landscapes, nature, and architecture.. What would we look like? What would that say about who we are?</li><li>Maybe you’re moss filled ruins, or an amethyst ridden dungeon– an abandoned lighthouse on the beach, an overgrown garden. . .</li><li>”Somewhere” is your nature equivalent.</li></ul>Won’t you take us Somewhere?<h2>Trained tokens</h2><ul><li>SDArt</li><li>agne</li><li>ohwx</li><li>bnp</li><li>atum</li><li>aved</li><li>bsf</li><li>aten</li><li>fcu</li><li>cees</li><li>chor</li><li>cna</li><li>nrf</li><li>elio</li><li>gani</li><li>pfa</li><li>kprc</li><li>kuro</li><li>asot</li><li>elis</li><li>bsp</li><li>psst</li><li>sqm</li><li>irgc</li><li>byes</li><li>dany</li><li>lpg</li><li>miro</li><li>avel</li><li>vaw</li><li>zaki</li><li>guin</li><li>pz</li><li>reys</li><li>crit</li><li>doa</li><li>suma</li><li>taku</li><li>ufos</li><li>phol</li><li>vedi</li><li>dds</li><li>weho</li><li>pte</li><li>oxi</li><li>yuck</li><li>zas</li></ul>Tokens for V1 :<ul><li>PoW Style</li><li>Token "nrgi" corresponds to the user "Eface#8250"</li><li>Token "mgti" corresponds to the user "Trash--Panda#6213"</li><li>Token "abiti" corresponds to the user "Itaaru#6818"</li><li>Token "datsi" corresponds to the user "bWm_nubby#6416"</li><li>Token "cavai" corresponds to the user "owleye#1290"</li><li>Token "hikoi" corresponds to the user "Guizmus#9881"</li><li>Token "cudii" corresponds to the user "Nerfgun3#7508"</li><li>Token "cepi" corresponds to the user "vcm07#7281"</li><li>Token "enigi" corresponds to the user "xThIsIsBoToXx#8765"</li><li>Token "difi" corresponds to the user "Eppinette-Chi#6220"</li><li>Token "arumi" corresponds to the user "H20_Dancing#8979"</li><li>Token "minhi" corresponds to the user "piscabo#8649"</li><li>Token "mdsi" corresponds to the user "alex1729#4669"</li><li>Token "plni" corresponds to the user "INF716 | Tobi#7518"</li><li>Token "tichi" corresponds to the user "katmoget#4491"</li><li>Token "uwei" corresponds to the user "DylanWalker#9705"</li><li>Token "fleri" corresponds to the user "Kazzear#7715"</li><li>Token "hepi" corresponds to the user "wpatzz#5836"</li><li>Token "wazi" corresponds to the user "Horvallis#7915"</li><li>Token "ouei" corresponds to the user "Cryonicus#8488"</li><li>Token "rithi" corresponds to the user "Dreamck#2108"</li><li>Token "mikii" corresponds to the user "discozouck#2695"</li><li>Token "sshi" corresponds to the user "espasmo#9486"</li><li>Token "gerai" corresponds to the user "dunkeroni#4269"</li><li>Token "inemi" corresponds to the user "Junglerally#3955"</li><li>Token "yohi" corresponds to the user "Lew39#1755"</li><li>Token "ronti" corresponds to the user "King Pendragon#3589"</li><li>Token "reemi" corresponds to the user "Akumetsu971#9982"</li><li>Token "eneii" corresponds to the user "tazi#2574"</li><li>Token "pethi" corresponds to the user "NorTroll#1798"</li><li>Token "wivi" corresponds to the user "Phaff#1970"</li><li>Token "maari" corresponds to the user "VereVolf#5658"</li><li>Token "eeti" corresponds to the user "Munkyfoot#7944"</li><li>Token "wrayi" corresponds to the user "Kaz#5485"</li><li>Token "afsi" corresponds to the user "crazykazoo#2431"</li><li>Token "opii" corresponds to the user "Ainvas#7625"</li><li>Token "pkgi" corresponds to the user "Trexdel#8281"</li><li>Token "budai" corresponds to the user "SmokeForce#4133"</li><li>Token "ibci" corresponds to the user "Sergio Santos#1447"</li><li>Token "ccui" corresponds to the user "Vil#0404"</li><li>Token "ucni" corresponds to the user "ResidentChiefNZ#6989"</li><li>Token "emiti" corresponds to the user "bitspirit3#1653"</li><li>Token "drui" corresponds to the user "CQ 🌸#9480"</li><li>Token "wrali" corresponds to the user "Chrisus#4937"</li><li>Token "aproi" corresponds to the user "Horsebird#3289"</li><li>Token "wboi" corresponds to the user "millennium_gun#6377"</li></ul>

SDArt : Somewhere

The total dataset is made of 46 pictures. It was trained on <a rel="ugc" href="https://huggingface.co/runwayml/stable-diffusion-v1-5">Stable diffusion 1.5</a>. I used <a rel="ugc" href="https://github.com/victorchall/EveryDream2trainer">EveryDream</a> to do the training, 100 total repeat per picture. The model is trained on the "PoW Style" token for every picture, and each picture has a secondary, arbitrary token.

Files with SHA256: 1fb55e028ee5dbccdf60bc1478617f6afbe90fddf8d71f0eea46f35a8f0c9529