flobbit's picture
Update README.md
765e736
|
raw
history blame
1.78 kB
metadata
license: apache-2.0
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
  - stable-diffusion
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - lora
widget:
  - text: >-
      f0rd66pu, truck, gold body, (lifted), massive orange volcano explosion in
      the background, night sky, tornado  (cfg = 8, seed = 2363198649)
inference: true
language:
  - en

ford-pickup-truck-1966-sdxl-lora

LoRA for SDXL 1.0 Base for generating 1966 Ford pickup trucks. 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:f0rd66pu_SDXL_v1_32:1>, then use the trigger keyword. Further example images with A1111 prompts at (https://civitai.com/models/151004/ford-pickup-truck-1966-sdxl)

Example diffusers prompt which you can run in the inference to the right: 'f0rd66pu, truck, gold body, (lifted), massive orange volcano explosion in the background, night sky, tornado (cfg = 8, seed = 2363198649)'

Recommended Weight:

1.0 (lowering the LoRA weight in A1111 will make it produce less accurate results)

Trigger:

f0rd66pu

Helper:

In general, you can vary the color of the body and make the truck lifted with some fiddling. For example: f0rd66pu, truck, blue body, (lifted), ...

Notes:

The LoRA seems to work well with other base SDXL models, but I didn't spend much time playing with this.

Methodology:

This model was trained on only 1966 images at 1024x1024. 122 images of a variety of vehicles (2wd and 4wd) and colors. No regularization images were used. 20 epochs with 4880 overall steps. No regularization images were used.