|
--- |
|
model: RoboDiffusionXL |
|
languages: |
|
- en |
|
license: openrail |
|
tags: |
|
- image-generation |
|
- lora |
|
- robot |
|
--- |
|
|
|
# Model Card for RoboDiffusionXL: Advanced Robotic Imagery LORA Model |
|
|
|
## Model usage |
|
|
|
This model must not be used at full strength but at approximately 70%. E.g. in Auto1111 and Forge... < lora:robodiffusionxl:0.7 > . |
|
|
|
## Example output |
|
![Example output](example.jpg) |
|
|
|
## The main keywords for this model are: |
|
- Quadruped |
|
- Hexapod |
|
- Octopod |
|
- Centiped |
|
- Aerial |
|
- Wheeled |
|
- Underwater |
|
|
|
Choose the appropriate keyword type for the desired motion type for the robot. |
|
|
|
## Model Details |
|
|
|
- **Model Name:** RoboDiffusionXL |
|
- **Version:** 1.0 |
|
- **Model Type:** Image Generative LORA Model based on SDXL Base |
|
- **Developers:** Fiacre |
|
- **Release Date:** May 20, 2024 |
|
- **Model Repository:** [Hugging Face Models Hub](https://huggingface.co/Fiacre/robodiffusion-xl-v1) |
|
|
|
## Overview |
|
|
|
RoboDiffusionXL is a LORA (Latent Optimization with Representational Adjustment) based on the SDXL (Stable Diffusion XL) architecture. It is specially designed for generating high-quality, diverse images of robots in various forms, including but not limited to wheeled, quadruped, hexapod, octopod, centipede, underwater, and aerial robots, across multiple artistic styles. |
|
|
|
## Training Data |
|
|
|
RoboDiffusionXL was trained on a high-quality synthetic dataset curated to include a wide variety of robotic forms and styles. The images include historical, cultural, and futuristic themes, ensuring diverse generated outputs. |
|
|
|
## Key Configuration and Settings |
|
|
|
- **Learning Rate:** 0.0009. |
|
- **Rank:** 256 (not so low rank), but was required otherwise the image were poor. |
|
|
|
## Limitations |
|
|
|
- Limited styles. |
|
- It cannot do triped, and quintaped robots well. |
|
|
|
## Licensing and Usage |
|
|
|
license: openrail |
|
|
|
## Future Work |
|
|
|
Future updates will include the introduction of triped and quintaped robots, alongside a broader array of diverse styles. The aim is to continuously expand the model's capabilities to cover an even wider spectrum of robotic forms and artistic interpretations. Community suggestions are appreciated. |
|
|