JavaScript required
We’re sorry, but Coda doesn’t work properly without JavaScript enabled.
Skip to content
Gallery
Root NTD
Main Page
Social Media Communities
Idea Sources
Quick Researches
Deep Researches
Projects
Side-Brand Developments - Technical Setup
Productising Development Process
More
Share
Explore
Deep Researches
AI language generation
Related Meetings
GPT-3
TextToImage Examples
Links and Sources
Ideas
Using Text to image AI’s came up while finding a lean way to generate title images for our Buildersdock Blog Posts.
Sell AI-Assisted Services
AI-generated blog posts?
‘If no code makes you a developer. AI-generated content makes you a producer.’
What do I use?
Premade Google Colabs
A Google Colab Notebook created by a
advadnoun
Uses DALL-E's discrete VAE (variational autoencoder) component to generate images.
A Google Colab created by
Bomze
utilizes CLIP (with CMA-ES optimizer) to steer BigGAN towards images that match a textual prompt in any language
A Google Colab Notebook by bonkerfield
Uses BigGAN to generate images/videos.
Generative Engine
made with
RunwayML
A storytelling machine that automatically generates synthetic images as you write new words and sentences
Computer Vision Explorer
Text-to-Image Generation
Datasets
Google's Conceptual Captions
Yahoo Flickr Creative Commons 100 Million (YFCC100m) dataset
Some first suggestions
After testing some TextToImage AI’s one can say that those AI
can
create an image which looks a little like the text one entered
BUT: You need to have a decent amount of imagination for those pictures
‘a brown dog’ looks like that:
Want to print your doc?
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
Ctrl
P
) instead.