div0-tank-sdxl-lora

LoRA for SDXL 1.0 Base for for generating images of the widely recognized Div0 tank... known as Div0 because $/quality results in a divide by zero error. People have generally given up on the tank, and are trying to find new uses for it. Hipsters generally avoid being seen in such a non-trendy ride. Common uses are demonstrated in the sample images. Can you discover more? The LoRA is in a safetensors format for use in diffusers or in UIs such as A1111.

How to use

In A1111, specify the LoRA in the prompt along with a weight <lora:vtnktnk_SDXL_v1_32-000015:1>, then use the trigger keyword. Further example images with A1111 prompts at (https://civitai.com/models/157883/div0-xl-tank-model)

Example diffusers prompt which you can run in the inference to the right: 'a (miniature) vtnktnk tank being used as a flower pot, dslr, 8k, beautiful, hyper realistic (cfg = 7.5, seed = 158618480)'

Recommended Weight:

1.0 (lowering the LoRA weight in A1111 will produce other effects)

Trigger:

vtnktnk

Helper:

In general you can generate a wide variety of tanks, characters, and scenes.

Notes:

The LoRA seems to work well with other base SDXL models.

Methodology:

This model was trained on only images at 1024x1024. No regularization images were used. 15 epochs with 5880 overall steps.