Text-to-Image AI Generated Prompts: ChatGPT vs. Google Bard

 

I recently came across a YouTube video in which its author compared images generated in Stable Diffusion XL with those generated in Midjourney.  There was nothing new there - such comparisons have been popping up all over the web during the past month.  What I found intriguing, however, was that the YouTuber used as prompts texts generated by ChatGPT based on only a single word.  I couldn't help wondering why the user had chosen GPT and not Google Bard which has lately been getting an equal amount of buzz.  I therefore decided to do a comparison of my own between the effectiveness of prompts generated by GPT from a single word as opposed to those generated in the same manner by Bard.  For this purpose, I limited myself to using SDXL as the sole image generator.

Going first to GPT, I asked the app to generate a prompt based on my own choice of word, in this case "beauty."  GPT immediately replied:

"Prompt: Create an AI-generated image that captures the essence of 'beauty' in nature.

Description: Imagine a serene landscape where beauty abounds. The image should showcase a harmonious blend of colors, shapes, and textures that epitomize the concept of beauty. Incorporate elements such as a stunning sunset or sunrise, vibrant flowers, majestic mountains, a serene lake, or any other natural elements that evoke a sense of awe and wonder. The goal is to convey the breathtaking beauty found in the natural world through an AI-generated image. Let your creativity and the power of AI bring this beauty to life!"

When I plugged this prompt into SDXL I got back the image shown below.  Just as GPT's prompt had been perfectly appropriate so was the image itself.  I thought it somewhat generic, though, and not particularly inspiring.

When I moved on to Bard I had a completely different experience.  Not only did the app provide five alternative prompts to the word "beauty" (each of them illustrated with watermarked images from, respectively, Open Art, Smithsonian, Unsplash, EarthSky, and Daily Hive) but before even beginning with those offered two unsolicited prompts of its own devising as follows:

"Sure, I can do that. Just give me a word and I will generate a prompt for you. For example, if you give me the word 'cat', I might generate a prompt like this:

A realistic 4k image of a cat sitting on a windowsill, looking out at the city skyline. The cat is wearing a red bow tie and has a content expression on its face."

"I can also generate prompts that are more abstract or creative. For example, if you give me the word 'dream', I might generate a prompt like this:

A surreal image of a dreamscape. The landscape is made up of strange and colorful shapes, and there are floating objects in the air. A figure is walking through the dreamscape, their face obscured by a mist."

I thought it pretty amazing that Bard could display such creativity.  As for the word "beauty," Bard suggested the following prompts:

"A realistic image of a field of flowers in full bloom. The flowers are a variety of colors, and they are swaying in the breeze. The sun is shining brightly, and the sky is a clear blue."

"A detailed image of a butterfly's wing. The wing is covered in intricate patterns, and it is reflecting the light in a beautiful way. The butterfly is perched on a flower, and its wings are slowly opening and closing."

"A stunning image of a sunset over the ocean. The sky is ablaze with color, and the clouds are reflecting the light in a magical way. The waves are crashing on the shore, and the seagulls are soaring overhead."

"A mesmerizing image of a nebula. The nebula is made up of gas and dust, and it is glowing with a beautiful light. The nebula is located in a distant galaxy, and it is millions of light-years away from Earth."

"A serene image of a mountain lake. The lake is surrounded by mountains, and the water is a clear blue color. The sun is shining brightly, and the trees are reflected in the water."

I was really floored by the versatility Bard showed in providing me with the above prompts and was in general very pleased with the images shown above that SDXL generated in response to them.  I intend to keep experimenting with Bard as a prompt generator and will continue to post here the images I obtain.