This model aims to imitate the style of Darkest Dungeon.Unlike <a target="_blank" rel="ugc" href="https://civarchive.com/models/124498/darkest-dungeon-sdxl-lora">this model</a>, it's not specifically aimed at mod development - instead, this is aimed at making standalone beautiful images in the style of the game.Do NOT ask what happened to version 001 and versions 004 through 009.I plan to add enemies and Darkest Dungeon 2 to the dataset in future versions, and maybe make a different LoRA for each individual hero. Actually, enemies are probably going to need a LoRA of their own, and even then I'm not sure if it'll get a good result. So enemies are planned for the far future.Finally, here's a tag directory:<ul><li>DarkestDungeon - activation keyword</li><li>DDCinematic - activation keyword for special part of dataset - only in version 010</li><li>DDHeroAfflicted - afflicted heroes - not in version 003</li><li>DDHero&lt;HERO_NAME_HERE&gt; - each individual hero - not in version 003 - only one image for each, so results are not guaranteed</li><li>DDAreaNone - the backgrounds of the Afflicted and cut Virtued images - these are the title screen and Hamlet respectively - again, small dataset means poor results</li><li>DDAreaWeald - the Weald - characterised by dead trees, mushrooms and broken stone walls</li><li>DDAreaCove - the Cove - characterised by coral columns on either side of the image, shipwrecks and weird "water" - I usually put this one in the negative prompt</li><li>DDAreaWarrens - characterised by an orange sky, sewer grates and skulls</li><li>DDAreaRuins - characterised by stone arches, scrolls and wood barrels</li></ul>

Darkest Dungeon SDXL

Do NOT ask what happened to versions 004 through 009This version aims to solve a number of problems with previous versions:<ul><li>Too little variety in generation because of a small, uniform dataset</li><li>Outputs occasionally look "low-resolution" because of the game's sprites being made at slightly less than 1024x1024</li><li>Too little interoperability with other LoRAs / base models</li></ul>This is done by adding a new dataset trained on frames selected from the game's two opening cinematics, and improving the quality of the existing dataset.Known limitations with this version:<ul><li>No longer very good at generating the game's iconic "Afflicted" scenes</li><li>Will often generate jagged edges, and is very biased towards creating deciduous trees</li></ul>Short keyword dictionary:<ul><li>DDCinematic - accesses the new dataset trained on the game's opening movies<ul><li>DDAncestor - tries to create a likeness of the Ancestor - not tested very much</li></ul></li><li>DDAreaCove - tries to create the Cove, seems inconsistent</li><li>DDAreaRuins - same but with the Ruins</li><li>DDAreaWarrens - same but with the Warrens</li><li>DDAreaWeald - same but with the Weald</li><li>DDAreaNone - tries to create a likeness of the Hamlet or the Darkest Dungeon as depicted from the game's title screen</li><li>DDHero&lt;HERO_NAME_HERE&gt; (e.g. DDHeroGraveRobber) - tries to generate the likeness of a specific hero - seems relatively inconsistent?</li></ul>The preview images are a little single-minded, so I'm eager to see what people can do with creative prompting, different base models and LoRA-mixing!To-do list for the dataset in future versions:<ul><li>The Flagellant, Shieldbreaker and Musketeer once I get their relevant DLCs</li><li>General graphics of the Crimson Court, Colour of Madness and Butcher's Circus DLCs</li><li>Darkest Dungeon 2<ul><li>The Runaway</li><li>The Duelist</li></ul></li></ul>

Files with SHA256: a174cfa7766bbea922ae384651169850f50e22db877d7e0adf4537c5acf6e0db