If you like our work, please consider supporting us so we can keep doing what we do. And as a current subscriber, enjoy this nice discount!
Also: if you haven’t yet, follow us on Twitter, TikTok, or YouTube!
In the past few years, transformers have become increasingly popular for generating text and images. This is because they are able to learn from large amounts of data and can develop high-quality results.
Sample the following three cases where machines were only given the text (prompt) and asked to generate text, images and code.
A) Prompt to Text
Prompt: Create a product recommendation for everyday series blog
Response: If you're looking for a new series to get into, I highly recommend the blog Everyday Series. It's a great resource for finding new and interesting series to watch, and it has something for everyone.
Prompt: Create a product recommendation for everyday series blog Response: If you're looking for a new series to get into, I highly recommend the blog Everyday Series. It's a great resource for finding new and interesting series to watch, and it has something for everyone.
The above text is created by Transformers based on the prompt provided
B) Prompt to Image
Prompt: Shahrukh Khan standing on a stage with open arms and with dark background and dim blue light at the back Response:
DALL-E creates the above text based on the prompt provided.
C) Prompt to Code
If you're looking for a way to generate text and images, you may want to consider using transformers. Transformers are a type of neural network that can be used for various tasks, including generating text and images.
There are a few different ways to use transformers for text generation. One is to use a pre-trained model, which you can find online. Another is to train your own transformer model. If you want to generate images, you can use a transformer to create an image from scratch or to edit an existing image. For example, you could use a transformer to add a moustache to an image of a person's face.
So far, text and images were being generated by Transformers to a high level of fidelity. Recently text to code went mainstream. We covered this two weeks back.
How about video?
Sample the following: