Juggernaut X I v11

Introduction

Juggernaut XI V11 by RunDiffusion is a text-to-image model available on RunDiffusion.com and accessible through an API on Octo.AI. It boasts advanced capabilities like improved aesthetics, enhanced text generation, and refined image quality.

Architecture

Juggernaut XI is built on the stabilityai/stable-diffusion-xl-base-1.0 model and is part of the diffusers library. It supports a diverse range of tags such as art, cinematic, and architecture. This version has been trained using the GPT4 Vision Captioning tool and features an expanded, cleaner dataset.

Training

• Training Tools: Utilizes GPT4 Vision Captioning by LEOSAM.
• Enhanced Features: Improved aesthetics, better handling of facial and bodily features, and enhanced text generation.
• Dataset: Contains higher quality images with improved classification of shots (e.g., full body, midshots, portraits).

Guide: Running Locally

1. Launch Fooocus on RunDiffusion: Visit RunDiffusion.com and access Fooocus.
2. Find and Use: Locate Juggernaut_XI_byRunDiffusion.safetensors to start generating images.
3. Prompting: Follow the guide by @Kandoo for simplified integration of the model's capabilities.

For optimal performance, consider using cloud GPUs such as those available from NVIDIA's cloud services or Google Cloud's GPU offerings.

License

The model is released under the CC BY-NC-ND 4.0 license, which restricts commercial use without permission. For business inquiries, commercial licensing, and more, contact RunDiffusion at juggernaut@rundiffusion.com.