LibGuides: Generative AI: AI Visualizers

Overview

Stable Diffusion (open source) and DALL-E (a product of OpenAI) are two of the dominant base models you'll find in many AI tools available online, including the ones listed on this guide; as with GPT, many tools are built using them with different names. Some of these tools generate images based on textual inputs (prompts), and some of these tools manipulate images (editing photos in various degrees, animating still photos, etc.) Still others move between text and image and vice versa. As with tools that incorporate audio cues, there's a great deal of potential within tools like these for increasing accessibility.

AI visual and video tools

Stable Diffusion
Stable Diffusion XL is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, cultivates autonomous freedom to produce incredible imagery, empowers billions of people to create stunning art within seconds.
more...less...
The AI image generator is free, but more advanced features will cost you.
Nightcafe
Nightcafe actually gives you access to several different image tools, including DALL-E.
Genmo
You can animate still images with this.
Craiyon
Think of this as DALL-E lite, sort of. One nice feature is that you'll get several versions of the finished drawing base don your text prompts.

FYI: Readings on visual AI tools

Real-time Sound Visualization using Generative AI
This is content from the Journal of Digital Contents Society, based in South Korea. 2023, OA.
Text-to-image generation using generative AI
From the International Journal of Scientific Research in Engineering and Management. August 2023.
Using the ID.8 framework (and several AIs) to create visual stories
ID.8 features a multi-stage visual story authoring workflow facilitated by generative AI. (1) The story creation begins with users
collaborating with ChatGPT to create a storyline and (2) manually editing of story content for finer edits. (3) Then, ID.8 automatically
parses the story co-created with ChatGPT into a scene-by-scene script to be edited further by the user. (4) The story scenes from
the script are automatically pre-populated and organized in the Storyboard and (5) edited in the Scene Editor where users use
StableDiffusion, AudioGen, and MusicGen to generate story elements and synchronize story element on the canvas and the timeline.
more...less...
This is a working paper, submitted to ACM (Association for Computing Machinery) and posted on the arXiv preprint server. Use with caution. I'm sharing it here because it's a good example of cross-platform AI use.

A weird product

Magale Man transformed by Genmo