The world ended, a long time ago. The sun cracked, the gates of death broke, and the earth became a cursed world. Still, humanity survives. Stuck in the crowded slums of the lightning-caged cities, your only hope for a decent life is to seize it for yourself. By blade or bullet; by a charming word or occult incantation: you will take this city or die trying, your broken body lying in the dark.
Update 23/6/13:
A smaller update. I fixed captioning issues and stretched out the dataset a bit. The biggest changes were from hyper-parameter optimization, so the model is both smaller and more true to the original style at high weights (with the right checkpoint of course).
Update 23/5/30:
I fixed a lot of issues, especially with the captioning. The model can now reproduce the original style at higher weights, and is overall more flexible. I will need to do more testing and figure out some way to expand the dataset before publishing a final version, but this update should be a major improvement.
Notes:
The trigger world bitdstyle is now impactful.
The recommended weights are lower. 0.6 - 0.8 should work well, although higher weights may give you interesting effects.
The monochrome effect has been somewhat disentangled from the general style, but you can guarantee it by adding "monochrome" to the prompt.
Original Post 23/5/28:
Hey folks,
This model is based on the art of the Blades in the Dark tabletop roleplaying game. This is an alpha release on a limited dataset, but I wanted to try applying the style to anime models. Right now, the LORA feels a bit overtrained in some areas and undertrained in others, but I feel that it offers a cool monochrome style. I decided to release what I have so far and then work on an improved version down the line.
This was trained on animefull, so it should have an impact on derived CLIP SKIP 2 models and merges. I tested with and was pretty happy with the results using Counterfeit V3. To get the monochrome effect, I recommend a weight of 0.8 - 1.0. There's no explicit trigger word, but using "silhouette" should get you closer to the style.
Thanks,
Machinique
Description
The model was trained on 24 512 x 768 images with 8 repeats up to epoch 20. After some testing, epochs 10 and 20 were merged at a 50% weight.
FAQ
Comments (3)
Oh man. One of the first big personal projects I tackled when I got the hang of SD was generating a bunch of style-adjacent images for Blades, in the absence of a trained model. I've still got all my old prompts for various factions and vices, so when I get a minute I'll throw this LoRA at them for sure.
Thanks! Right now, this is just trained on art from the core book, but I am going to be looking at supplementing it with training data from supplements and fan art. It hasn't been trained on game concepts yet, but I will look into that for future versions.
Looking forward to your update
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.