Darkest Dungeon SDXL版本010 (ID: 464855)

This model aims to imitate the style of Darkest Dungeon.

Unlike this model, 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:

• DarkestDungeon - activation keyword

• DDCinematic - activation keyword for special part of dataset - only in version 010

• DDHeroAfflicted - afflicted heroes - not in version 003

• DDHero<HERO_NAME_HERE> - each individual hero - not in version 003 - only one image for each, so results are not guaranteed

• DDAreaNone - the backgrounds of the Afflicted and cut Virtued images - these are the title screen and Hamlet respectively - again, small dataset means poor results

• DDAreaWeald - the Weald - characterised by dead trees, mushrooms and broken stone walls

• 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

• DDAreaWarrens - characterised by an orange sky, sewer grates and skulls

• DDAreaRuins - characterised by stone arches, scrolls and wood barrels

描述:

Do NOT ask what happened to versions 004 through 009

This version aims to solve a number of problems with previous versions:

• Too little variety in generation because of a small, uniform dataset

• Outputs occasionally look "low-resolution" because of the game's sprites being made at slightly less than 1024x1024

• Too little interoperability with other LoRAs / base models

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:

• No longer very good at generating the game's iconic "Afflicted" scenes

• Will often generate jagged edges, and is very biased towards creating deciduous trees

Short keyword dictionary:

• DDCinematic - accesses the new dataset trained on the game's opening movies

  • DDAncestor - tries to create a likeness of the Ancestor - not tested very much

• DDAreaCove - tries to create the Cove, seems inconsistent

• DDAreaRuins - same but with the Ruins

• DDAreaWarrens - same but with the Warrens

• DDAreaWeald - same but with the Weald

• DDAreaNone - tries to create a likeness of the Hamlet or the Darkest Dungeon as depicted from the game's title screen

• DDHero<HERO_NAME_HERE> (e.g. DDHeroGraveRobber) - tries to generate the likeness of a specific hero - seems relatively inconsistent?

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:

• The Flagellant, Shieldbreaker and Musketeer once I get their relevant DLCs

• General graphics of the Crimson Court, Colour of Madness and Butcher's Circus DLCs

• Darkest Dungeon 2

  • The Runaway

  • The Duelist

训练词语: DarkestDungeon