A SDXL 1.0 LoRa made by AI_Characters based on the official artwork for the "fantasy extraction shooter" game Dark and Darker by Ironmace, which can be found here.
The model can alternatively also be found on CivitAI!
Usage recommendations
-
Weight: 1.0 (may need to be adjusted down when using in conjunction with other LoRa's)
-
Model: SDXL 1.0 with 0.9 vae
-
Generation parameters: 35 steps | DPM++ 2M Karras | CFG 7
-
Negative prompt: text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast with only the "G" text encoder enabled (see my article here for how to do that)
Trigger words
- "artwork in imst artstyle"
Samples
For the generation data of these samples such as prompts and sampler settings please see the samples on the model's page on CivitAI here]!
Changelog
-
v2.0
- Complete revision - trained with a much lower learning rate but more epochs, leading to increased likeness, flexibility, and variety; added 12 official artworks of the various ingame classes which no longer exist ingame
-
v1.0
- Initial release
Additional Info
Credit is not mandatory but I would still appreciate credit when posting images using these LoRa's on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!
I share all of my model's and training knowledge for free, but donations to my Ko-Fi would be greatly appreciated! Testing so much and training so many model's costs a lot of money (and time).
Feel free to also try out my RVC2 AI voice models which you can find here!
See here for an extensive article about my entire training workflow and configuration if you want to train your own SDXL 1.0 LoRa's and achieve results similar as me!
Stats (v2.0)
Dataset:
- 26x artworks
Epoch chosen for the final model:
- 50
Learning rate:
- 3e-6
For more info - including the training configuration used - see the article linked at the end of the "Additional Info" section.
