Text2image Prompt Generator

🚀 GPT - 2 Prompt Generator for Text - to - Image Models

This project presents a GPT - 2 model fine - tuned on the succinctly/midjourney-prompts dataset. The dataset includes 250k text prompts that users sent to the Midjourney text - to - image service over a month. For more details about how this dataset was scraped, refer to Midjourney User Prompts & Generated Images (250k). This prompt generator can be used to auto - complete prompts for any text - to - image model, such as those in the DALL·E family.

🚀 Quick Start

This prompt generator can be used to auto - complete prompts for any text - to - image model (including the DALL·E family):

✨ Features

• Versatile Compatibility: Can be used with any text - to - image model.
• Midjourney - Specific Insights: Although it can work with all text - to - image models, it sometimes generates Midjourney - specific tags.
• Customizable Output: Users can specify requirements using double - dashed parameters or set entity importance via explicit weights.

📄 License

This project is licensed under the "cc - by - 2.0" license.

⚠️ Important Note

While this model can be used with any text - to - image model, it may occasionally produce Midjourney - specific tags.

💡 Usage Tip

When using this model, please attribute credit to Succinctly AI. You can specify certain requirements via double - dashed parameters (e.g., --ar 16:9 sets the aspect ratio to 16:9, and --no snake asks the model to exclude snakes from the generated image) or set the importance of various entities in the image via explicit weights (e.g., hot dog::1.5 food::-1 is likely to produce the image of an animal instead of a frankfurter).