Image Prompt Helper danube3 500 M

Introduction

The ImagePromptHelper-danube3-500M is a text generation model designed to assist in generating art-focused prompts. It leverages various datasets to create detailed, context-rich descriptions, suitable for artistic scenarios.

Architecture

The model is based on the h2oai/h2o-danube3-500m-base architecture and utilizes the transformers library. It is trained on datasets such as k-mktr/improved-flux-prompts and Gustavosta/Stable-Diffusion-Prompts to enhance its capability to generate art-related text prompts.

Training

Thanks to the support of the Florence-2-large-PromptGen-v1.5 model by MiaoshouAI, a specialized SFT dataset was created for training ImagePromptHelper-danube3-500M. This dataset includes a variety of prompt styles and detailed descriptions, improving the model's output quality.

Guide: Running Locally

1. Setup Environment

   • Ensure you have Python installed.
   • Install the transformers library:

     pip install transformers
     

2. Download Model

   • Use the following command to pull the model:

     ollama pull trollek/imageprompthelper-danube3-500m
     

3. Run Inference

   • Use your downloaded model to generate prompts by initializing it with your preferred settings and input prompts.

4. Cloud GPU Recommendation

   • For efficient processing, consider using cloud GPU services like AWS, Google Cloud, or Azure.

License

The ImagePromptHelper-danube3-500M is licensed under the Apache-2.0 License, allowing for wide use and distribution with proper attribution.