Creating images with your trained AI model on Gerhard is a straightforward process. Here’s how you do it:
Select your trained model: Start by choosing the trained model you want to use from your dashboard.
Enter your prompt: In the new window that opens, you’ll find a prompt field where you can describe the image you want to create.
Choose the image ratio: You can select the desired aspect ratio for your output image, such as square, landscape, or panorama, depending on your needs.
Adjust the model strength: Use the strength toggle to control how strictly the model adheres to the trained assets. A value of 1 or above means the model will closely follow the style of your uploaded images, producing results that are highly consistent with your training set. Values below 1 allow the AI to be more creative, blending your style with other elements for more varied outcomes.
Generate and choose: Once you’ve set everything up, generate the images. Gerhard will produce four images based on your input, from which you can select the one you like best. You can then upscale it to 4K if desired and download it for use.
This process allows you to fully leverage the potential of your trained models, giving you creative control over the final output while exploring variations in your style.
