AI Image Generation

The AI Image generation feature enables content owners to generate course, course template, learning path and media images using AI. Users can review the generated image and decide whether to save it, generate a new one, or upload an image manually, if needed. imc uses Microsoft Azure OpenAI Service (DALL-E3) . The prompt to generate the image uses the component name and description of the respective course, course template, learning path and media as well as an additional hard-coded text to optimize the result.

Workflow

1. Go to client administration to activate the usage of AI

2. Navigate to the Courses manager, click the desired course and select “Edit”

3. You are redirected to the course “Description” tab

4. Input a name and a description.

5. Click on generate image to open the image generation window.
   

   

6. Click on generate image (can be repeated)
   

   

7. Choose between generated image, including the previously uploaded image and use selected.

Feedback on the AI Image Generation Feature

The feedback feature is designed to allow admins to provide feedback (thumbs up or thumbs down) on AI-translated text. This functionality enables admins to decide if the new feature meets their expectations.

Under the generated image button feedback options are displayed:

• Thumbs up - for positive feedback

• Thumbs down - for negative feedback/ improvements needed

Clicking on thumbs up will send the feedback immediately without further action.

Clicking on thumbs down will trigger a modal, where the user can explain his experience with the translation service. After the feedback is submitted, a confirmation message is displayed: "Thanks for your feedback!"

Limitation

The image generation takes up to 40 seconds, which is caused by the time Microsoft Azure OpenAI Service DALL-E3 requires to generate an image.

Privacy and Data Security

The prompts (inputs) including component name and description of the respective course, course template, learning path and media and completions (outputs):

• are NOT available to other customers.

• are NOT available to OpenAI.

• are NOT used to improve OpenAI models.

• are NOT used to train, retrain, or improve Azure OpenAI Service foundation models.

• are NOT used to improve any Microsoft or 3rd party products or services without your permission or instruction.

• Your fine-tuned Azure OpenAI models are available exclusively for your use.

The Azure OpenAI Service is operated by Microsoft as an Azure service; Microsoft hosts the OpenAI models in Microsoft's Azure environment and the Service does NOT interact with any services operated by OpenAI (e.g. ChatGPT, or the OpenAI API).