, spotlight, street, Chic slender Ming Dynasty (monster_1.2) , FOV 90 degrees, detailed art, (by Junji.jpeg)
, scary, horror, flashlight, arafed slender man in a dark hallway with a light shining on it, concept a.jpeg)
, scary, horror, flashlight, a close up of a dog in the dark with a camera, concept art by Hieronymous.jpeg)
, slender monster arafed in the dark on the street at night, a photo by Minerva J. Chapman, cgsociety, serial art.jpeg)
 , FOV 90 degrees, detailed art, (by Junji Ito_1.1) , Grim, Knightcore, Black lig.jpeg)
Type | |
Stats | 781 |
Reviews | (155) |
Published | Oct 20, 2023 |
Base Model | |
Training | Steps: 6,200 Epochs: 1 |
Usage Tips | Clip Skip: 1 |
Trigger Words | <lora:deathia_yiu_v20:0.9> Deathia |
Hash | AutoV2 AE8CFB6778 |
How to use
It is recommended to write the following tokens: deathia, blurry, dimmed, lowkey, night, scary, horror, low quality, flashlight, monster.
Copy the prompt and parameters from the preview to this model — you will not lose.
What the model is suitable for
The model trained on low-quality images depicting freaks, monsters, horror stories and abandoned houses.
LoRA was trained on a variety of examples, so try combinations and share your creativity in the comments.
I trained LoRA on the Deliberate_v3 model, so it's better to work with her in pairs.
to get a realistic result with the bluer effect, you need to set as few sampling steps as possible and lift the CFG Scale.
Generation at high resolutions is possible.
Which model works best with
It is best to use the Deliberate_v3 model, but you can combine this LoRA with other solutions focused on photorealism, model will work perfectly with them.