Images and multimedia can be used to enrich your research and topic presentations. When searching for and using images, you will want to keep the following tips in mind:
For information about video and audio elements, check out our Streaming Media Guide.
The following image platforms make it easier to cite and attribute properly, since rights and permissions are often stated for each image.
Several generative AI tools exist for creating images using text-to-image prompts. Only use AI generated images in your academic work if you have permission from your instructor (or the topic of your work is generative AI). Although AI artwork is not protected by copyright law, you will need to cite the software and document the prompt you used to generate the image.
Example of image generated using the prompt "Lion's Mane Jellyfish":
Canva. (2023). Text-to-Image (2022 Version). https://www.canva.com/your-apps/text-to-image
Different AI Image Generators
This table provides an overview of popular AI tools for generating images and videos. Each platform offers unique features tailored to different creative needs. Explore the tools below to find the one that suits you.
| Tools | Developer(s) | Features | Cost of Use |
|---|---|---|---|
| DALL-E | OpenAI | A version of GPT-3 trained to generate images from text descriptions, using a dataset of text-image pairs. DALL-E is capable of combining unrelated concepts in plausible ways, rendering text, and applying transformations to existing images. | Purchase a plan for use |
| Midjourney | Midjourney, Inc. | Midjourney makes images from scratch using prompts, and can generate variations of existing images using tools such as 'Upscale,' 'Reframe,' and 'Repaint' to refine and experiment with different presentations of an original image. Midjourney also can make adjustments to the aspect ratio, stylization, and variety of images in one's portfolio. Users of the AI can also collaborate with others on image generation projects using shared spaces built within the chat tab of the platform. | Purchase a plan for use |
| Stable Diffusion | Stability AI | Stable Diffusion is a generative artificial intelligence (AI) model that can be used to create detailed, photorealistic images from text descriptions; restore or add to specific regions of an image; create images that extend beyond the original image; create translations guided by a text prompt; and, create videos and animations. | Purchase credits for use |
| Microsoft Designer | Microsoft Company | Microsoft Designer can be used to create custom images for an assortment of personal projects, make cards or other pieces of art to share with others, create seasonal wallpaper and backgrounds for electronic devices, and make coloring pages and other interactive pieces of art. |
Free version Purchase advanced features |
| Adobe Firefly | Adobe Inc. | Adobe Firefly can be used to add detailed elements to preexisting images in Adobe Photoshop using the Generative Fill application. It can also be used to create high-quality images in Adobe Firefly with photorealistic details and various mood and lighting characteristics. The AI tool also enables users to modify videos in Adobe Premiere Pro by adding frames, lengthening ambient audio, and/or eliminating awkward cuts. Adobe Firefly also generates video clips from photos or text prompts. |
Free version Purchase credits for more features |
| Ideogram | Ideogram AI Inc | Ideogram can be used to edit specific regions of images to replace objects, add text, fix imperfections, change backgrounds, and generate high-resolution details. It also can be used to combine images into a unified composition using Magic Fill, and adjust the image composition and aspect ratio of any image to fit any screen size without compromising the original content. |
Free version Purchase for advanced features |
| Runway | Runway AI, Inc. | Runway is an AI image generator that includes 34 individual AI tools, including Text-to-Image, Image-to-Image, Generative Video. Its Gen-3 Alpha model is useful for high-fidelity, fast and controllable video generation. |
Free version Purchase advanced features |
| Craiyon | Craiyon LLC | An AI image generation tool that requires no login. |
Free version Purchase for advanced features |
St. Catherine University. (n.d.) [Photograph of Our Lady Victory Chapel]. https://cdm17519.contentdm.oclc.org/digital/collection/
A digital library of more than 1 million of images in the areas of art, architecture, the humanities, and social sciences
Images in the public domain are not restricted under copyright, which means you do not need to obtain permission to use them in your work.
Note: You should always cite the images in your work, even if it's available in the public domain.
Stock photography should reflect a diverse and inclusive range of people. The following sites focus on highlighting images of marginalized populations. Including these images in research presentations reinforces the idea that everyone should be seen.
St. Catherine University. (n.d.). Students (6) behind a tree in front of Derham Hall [Photograph]. https://cdm17519.contentdm.oclc.org/digital/collection/cscphoto/id/37/rec/15
©2024 St. Catherine University Library, St. Paul, Minnesota, USA
