Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

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.

Some of the preview images may use LoRAs which are not yet released.

Character images will usually require img2img, due to the weight of background images in the dataset.

Some good weights are:

  • 003 on its own with a weight of 1.25 or 1.5

  • 002 and 003 in combination with a weight of 1 for 002 and 0.75 for 003

  • 003 combined with any other LoRA with a weight of 1.25

Version 003 has no character images, so it tends to be more useful than 002 on backgrounds.

Version 002 is heavily biased towards the poses and lighting of characters suffering an Affliction - that means strong red highlights.

All the Affliction images used the same exact background (which I may fix in future versions), so 002 will tend to add traits of that background unless you put DDHeroAfflicted in the negative prompt.

There's no version 001, cause I tried to train it with Virtued, Afflicted and background images, and it sucked.

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, but right now I'm still green in terms of SDXL LoRA training, so those are being saved for when I have more confidence.

Finally, here's a tag directory:

  • DarkestDungeon - activation keyword

  • DDHeroAfflicted - afflicted heroes - only in version 002

  • DDHero<HERO_NAME_HERE> - each individual hero - only in version 002 - 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

Images Generated With This Model

Loading...

Similar Models

Half-Life 2 Concept Art
V1
Half-Life 2 Concept Art
(5.00)
0
1 Ratings
Team Fortress 2 Textures
V1
Team Fortress 2 Textures
(0.00)
0
0 Ratings
Team Fortress 2 Textures XL
V2
Team Fortress 2 Textures XL
(0.00)
0
0 Ratings
ClassipeintXL (oil paint / oil painting style)
V2
ClassipeintXL (oil paint / oil painting style)
(0.00)
0
0 Ratings
Team Fortress 2 Textures
V1
Team Fortress 2 Textures
(5.00)
0
3 Ratings

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.