Sdxl Dpo Turbo

🚀 Merge of SDXL Turbo & SDXL DPO

This project is a merge of SDXL Turbo and SDXL DPO, a text - to - image solution. It offers high - quality image generation with specific parameters and can be used in multiple platforms.

🚀 Quick Start

✨ Features

• It is a text - to - image model, tagged with text - to - image, turbo, stable - diffusion, stable - diffusion-xl, and dpo.
• It comes with a widget example where you can input text like 'rusty robot cartoon' to get an output image.
• It provides inference with specific parameters, such as setting the num_inference_steps to 8.

📦 Installation

You can download the *.safetensors file for use in AUTOMATIC1111, ComfyUI, InvokeAI. Download *.safetensors file

💻 Usage Examples

Basic Usage

from diffusers import AutoPipelineForText2Image
import torch
        
pipeline = AutoPipelineForText2Image.from_pretrained('thibaud/sdxl_dpo_turbo', torch_dtype=torch.float16).to('cuda')        
image = pipeline('A mecha robot in a favela', num_inference_steps=2).images[0]

📄 License

The project uses an other license. Please read their licences before using it.

📋 Information Table

⚠️ Important Note

Read the licences of SDXL Turbo and SDXL DPO before using this project.