---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- fluxgym
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: prci
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
widget:
- text: prci, red mercedes c class, standing on a bricked pavement
  output:
    url: images/example_ziqkc20v9.png
- text: >-
    Photorealistic photo of prci, gray nissan qashqai, standing on a grey brick
    pavement, trees and blue sky in the background. Taken by phone
  output:
    url: images/example_88v40fgl6.png

---

# Photorealistic Car Images

A Flux LoRA trained locally on dataset of various low/midrange cars close-up photos with [Fluxgym](https://github.com/cocktailpeanut/fluxgym)

You can use it to get better quality of car photos with realistic reflections, and more realistic backgrounds.

<Gallery />

## Trigger words

You should use `prci` to trigger the image generation with lora.

Recommended prompt format is:

"prci, [car color, brand, model], [environment/background description]"

## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.

Weights for this model are available in Safetensors format.