---
license: apache-2.0
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - lora
inference: true
---

# toyota-4runner-1st-gen-sdxl-lora

![](00170-2254940999.png)

A LoRA for SDXL 1.0 Base for generating 1st gen 4runners. The LoRA is in a `safetensors` format for use in diffusers or in UIs such as A1111.

## How to use
In A1111, add LoRA in prompt along with a weight <lora:4runner1_SDXL_v1:0.8>, then use the trigger keyword.

Example diffusers prompt which you can run in the inference to the right: '4runner1, (quartering in view), (red:1.9) body, lifted, modified, topper off, ((chrome stock spoke wheels):1.9), blue sky, driving on the (beach:0.8), (ocean0.8), (sunset:0.8),8k, uhd, dslr, perfect focus  (cfg = 4, seed = 410282563)'

## Recommended Weight: 
0.8 (lowering will make it hybridize with newer 4runners)

## Trigger: 
4runner1

## Helper: 
In general you can vary the color of components (body, topper, wheels, grill, bumper) with some fiddling. Also, lifted vehicles can be generated with lifted, modified. The following view tags were used in training although it might be hard to generate images with these specific views: 'quartering away view', 'quartering in view', 'front view', 'rear view', 'side view'.

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

## Methodology:
This LoRA was trained on only 1984-1985 images at 1024x1024. 92 images of vehicles and one modified vehicle. Two epochs with 1656 steps each. No regularization images were used.

## Examples:
Further example images with A1111 prompts at (https://civitai.com/models/147916/toyota-4runner-1st-gen-sdxl)

![](00342-3664327997.png)