This section provides a brief overview of popular tools. The tools are described for information purposes only and are not an endorsement. Please consult with your instructor, supervisor, and journal publication for their generative AI usage policies. Approach usability and application with caution and discretion.

The University of Illinois Urbana-Champaign's Technology Services department provides a list of approved resources on their Generative AI Resources page. Any application not on their list is not approved and should not be used with University solutions or devices.

Last Updated: June 2024

What is DALL-E 2 and DALL-E 3?

DALL-E 2, developed by Open AI, is a generative AI tool that generates images from text descriptions. It can apply artistic concepts and styles to generative images based on the input. Users must purchase credits to generate images through prompts, edit requests, or request image variations. The current base rate for credits is 115 credits for every $15. Pricing information is available on OpenAI's Pricing page in the image models section.

Similar to GPT4, DALLE-3 is an updated and improved version that is available to ChatGPT Plus and Enterprise users. Microsoft has incorporated DALL-E 3 into Bing’s Image Creator tool.

Considerations

As with other tools, do not share or input personal or confidential information. As of this LibGuide's last update, creators can opt their images out from training models through OpenAI's Artist and Creative Content Owner Opt Out form.

• Character limit for DALL-E 2 is 1,000 and 4,000 for DALL-E 3. 
• Both versions require payment or a subscription to use.
• Generative AI art tools are trained to scrape content from human artists without their knowledge or permission (review copyright information in the Legal Issues page).
• Open AI Universal Policies
  • compile with applicable laws
  • don’t use the services to harm yourself or others
  • don’t repurpose or distribute output to harm others 
  • respect the OpenAI guidelines

How can I access DALL-E?

Trial access to DALL-E 2 is available through the Center for Innovation in Teaching & Learning (CITL) Innovation Studio. 

Example Prompts

"DALL-E: Creating images from text" page provides some example prompts. Below are some prompts that can be used with Microsoft Copilot:

• A goat wizard wearing a purple jacket for a Dungeons & Dragons campaign
• Bento box art of a smiling cat

What is Midjourney?

Midjourney is a generative AI program that produces images based on text and other images. Midjourney Inc. designed the tool using text-based prompts with Discord bot commands.

Midjourney Models Available

All models are subscription-based. Visit Midjourney's Subscription Plans page for information.

Considerations

As with other tools, do not share or input personal or confidential information. Review Midjourney's Privacy Policy for information on what data is collected, which varies on location.

• Midjourney Terms of Service
• Users must have a Discord account
• Requires a monthly or yearly subscription plan.
• Some subscription options will post your creations to the shared Midjourney Discord, even if you are using the bot on a private discord server.

How can I access Midjourney?

Trial access to Midjourney is available through the Center for Innovation in Teaching & Learning (CITL) Innovation Studio. 

Midjourney requires a Discord account to use the program. Discord is an instant messaging social media platform with group voice call, video call, and text messaging capabilities and is immensely popular among online gamers. Midjourney offers monthly and yearly subscription plans at different levels.

Example Prompts

Midjourney's Prompts page provides information on how to write prompts for this platform. Below are some prompts that can be used with Microsoft Copilot:

• A cat in the style of Picasso
• Album cover for a band about the digital humanities

What is Stable Diffusion?

Stable Diffusion is a text-to-image open-source generative AI tool created by Stability.Ai. Stable Diffusion offers a free membership model for non-commercial and personal use, as well as paid professional and enterprise memberships.

Stable Diffusion Models Available

All models are subscription-based. Visit Stable Diffusion's Pricing Plans page for information.

Considerations

Consult Stable Diffusion's Privacy policy page for information over what personal data is collected.

• Open-source code can run locally on a machine
• The base stable diffusion models can be expanded with a variety of “plugins”! The easiest way to experiment is with one of the below GUI systems
  • ComfyUI
  • Automatic1111
  • RunDiffusion offers a handy platform with many of these tools pre-installed

How can I access Stable Diffusion?

Access to local versions of StableDiffusion available via consultation with the SCIM Lab.

Example Prompts

Below are some prompts that can be used with Stable Diffusion:

• Oil painting of a gerbil, sitting down, surrounded by large fruit, pastel colors
• A beautiful corgi, chasing a frisbee, wearing bowtie, small top hat, park background, cartoon, cute