Image AI

Image AI is a generative AI tool for creating visual content. It supports text-to-image generation, where a natural-language prompt is transformed into a new image, and image-to-image transformation, where an existing image is modified or restyled according to a prompt or style reference. As with other GWDG services, users’ data is kept secure and is not stored or used to train AI models. The simple, user-friendly web interface makes generating and saving images easy.

Current Models

Image AI provides state-of-the-art open-weight models which are hosted on our platform with high standards of data protection. The data sent to these models, including the prompts and images, are never stored at any location on our systems.

Available models are regularly upgraded as newer, more capable ones are released. We select models to include in our services based on user demand, cost, and performance across various benchmarks. Certain models are more capable at specific tasks, which are described below to the best of our knowledge.

Web interface and usage

The web interface can be reached here.

Here is a brief description of the components of the web interface:

• Model selection: Choose the model you want to use.

• Prompt: Enter your text description to generate an image.

• Upload: Upload an image to use with the image-to-image model.

• Advanced options: Set the width, height, and number of output images.

Open-weight models, hosted by GWDG

FLUX.1-schnell

FLUX.1-schnell is a fast, high-performance text-to-image generation model optimized for speed while maintaining strong visual quality. This model is developed by Black Forest Labs.

Key capabilities:

• Rapid generation of images from text prompts.
• Maintains coherent composition and style despite the speed focus.
• Supports diverse artistic and photorealistic outputs.
• Good at rendering complex scenes with reasonable fidelity.

You can find more details about this model on this page.

Qwen-Image-Edit

The Qwen-Image-Edit model takes images and a text prompt as input. You can upload an image and edit it by providing a text description as a prompt. Its capabilities for both semantic and appearance editing make this model a powerful tool for image modification. Another key feature is the ability to add, delete, or modify text within your uploaded image. You can find more details about this model on this page.

Data Privacy

With user authentication via SSO and by running the service on GWDG’s HPC infrastructure, we ensure the privacy and security of user data.