---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- flux
- flux.1-dev
- automotive-design
- industrial-design
- design
- agent-friendly
widget:
- output:
    url: assets/covers/CRT_Ext_SUV_Rough.webp
  text: 'xonar_ext_SUV_rough, A professional studio photography of a SUV, silver metallic gloss paint, 8k resolution, cinematic lighting, dark grey studio background.'
- output:
    url: assets/covers/CRT_Int_Concept2.webp
  text: 'xonar_int_concept, Photograph of a futuristic car interior with a sleek, minimalist design. The dashboard features a red and black color scheme with a white steering wheel and a central console. The seats are upholstered in light gray fabric with red accents. The background shows a sandy, desert-like terrain.'
- output:
    url: assets/covers/INS_Inspiration01.webp
  text: 'xonar_ext_odd, A professional studio photography of a concept car, silver metallic gloss paint, 8k resolution, cinematic lighting, dark grey studio background.'
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
license: apache-2.0
language:
- en
- zh
pipeline_tag: text-to-image
---
# OLOID Framework

<Gallery />



<!-- README.md -->

[English](./README.md) | [中文](./README.zh-CN.md)

## About OLOID
OLOID Framework is an open-source LoRA framework for automotive design generation.

Built on Flux.1 dev, it is designed for agent retrieval and invocation, aiming to hand over the tedious parameter-tuning process in design gacha (LoRA stacking + seed sampling) workflows to agents and free up designers’ time.  
It also supports manual combination and use by designers.



## Framework Structure
The current release includes 49 LoRAs, organized across four dimensions and designed to be combined based on different design goals.  
For example: PRD (define volume) + CRT (add form language) + INS (expand creative possibilities) + VIS (control visual output)

| Dimension | Code | Role |
| --- | --- | --- |
| Production | PRD | Production-oriented volume, proportion, and structural foundation |
| Creative | CRT | Advances form language and design variation |
| Inspiration | INS | Introduces cross-domain design language and additional stimulus |
| Visuals | VIS | Controls image style, material feel, and overall visual impression |

A full structural overview is shown below:
![Structure](./assets/Structure.webp)
*Figure: Full structure across PRD / CRT / INS / VIS and EXT / INT / PART.*



## Index
For each LoRA’s trigger words, reference prompts, and recommended weights, please refer to the index:

- [Huggingface](./INDEX.md)
- [Feishu Doc](https://ucnd3tftqho9.feishu.cn/wiki/UUe5wZy9CiaQspkNEErcuzMqnie)



## Download
- [Download](/XonarLabs/OLOID_Framework/tree/main) them in the Files & versions tab.



## Project Status
The current phase of OLOID on Flux.1 has been completed. We have already moved on to exploring next-generation model training and a more complete agent-oriented workflow, so this generation will no longer be updated.  
Feedback and testing are welcome.

For discussions around AI generation systems for automotive design, please contact OkeyDesign: hello@okeydesign.com  
For custom training, agent-related and other technical topics, please contact XonarLabs: info@xonarlabs.com



## License
This model is built on FLUX.1 dev.  
Usage may be subject to the base model's license restrictions.



## Credits
OkeyDesign & XonarLabs