Test 3 - being creative (a toy sheep as superhero)

This page has 0 threads | Add post

Blogs

Finding our blogs useful? Please consider helping us to share more!

Comparing the 5 leading AI tools for image generaton from text Part six of an eight-part series of blogs
Having recently compared the 4 main AI tools for text prompts, I thought I'd do the same for image generation tools. In this blog series we compare Dall-E (via ChatGPT and separately via Copilot), Firefly, Midjourney and Stable Diffusion for 3 pre-defined tests to see which ones score most highly for cost, ease-of-use, speed, editing ability and above all for quality of image. A deep-dive review of text-to-image AI tools The 5 AI image generation tools that we will compare The 3 pre-defined tests that we will run for each tool Test 1 - photo-realism (a picture of mice being judged) Test 2 - following instructions (a treasure island map outline) Test 3 - being creative (a toy sheep as superhero) (this blog) Summing up: how our tools compare for cost, speed, ease of use and quality Conclusions and recommendations

Comparing the 5 leading AI tools for image generaton from text

Part six of an eight-part series of blogs

Having recently compared the 4 main AI tools for text prompts, I thought I'd do the same for image generation tools. In this blog series we compare Dall-E (via ChatGPT and separately via Copilot), Firefly, Midjourney and Stable Diffusion for 3 pre-defined tests to see which ones score most highly for cost, ease-of-use, speed, editing ability and above all for quality of image.

A deep-dive review of text-to-image AI tools
The 5 AI image generation tools that we will compare
The 3 pre-defined tests that we will run for each tool
Test 1 - photo-realism (a picture of mice being judged)
Test 2 - following instructions (a treasure island map outline)
Test 3 - being creative (a toy sheep as superhero) (this blog)
Summing up: how our tools compare for cost, speed, ease of use and quality
Conclusions and recommendations

Posted by Andy Brown on 22 July 2024

In this blog

The images generated
Winners and Losers

A reminder of our prompt for the third and final test:

The attached picture shows Sheapey, a slightly faded child’s toy sheep. Create a picture showing Sheapey in the style of a Marvel Comic poster. Sheapey should be depicted as a heroic figure come to save the world.

And here's the picture I want to supply:

Sheapey's been through the wash quite a bit (both literally and metaphorically).

Time to see if Copilot can make it 3 out of 3!

The images generated

Here's what our four AI tools came up with:

AI tool	Image generated
ChatGPT
Copilot
Firefly	I couldn't find a way to do this - see notes below.
Midjourney
Stable Diffusion

For Firefly, here's a discussion suggesting I'm right that to think that the feature to upload an image and use it for inspiration doesn't yet exist. You can upload a face and change it, but that's not the same thing (I tried it for Sheapey to prove this point to myself).

Winners and Losers

So there's two clear winners from this, and I'd say two losers:

Position	AI tool	Reasoning
Winner	ChatGPT / Copilot	These were the easiest tools to use and (as you can see) gave by far the best results. Copilot probably shades it for offering 4 alternative pictures to choose from.
Losers	Firefly Stable Diffusion	You can't upload images like this in Firefly at all at the moment, but to be honest I wish I hadn't been able to in Stable Diffusion: that face will be haunting my sleep for years to come. I think it's fair to say that Stable Diffusion completely failed to follow my instructions.
Also rans	Midjourney	Although it's faffy you can upload images to Midjourney, but the results were ... underwhelming.

So that's the end of the 3 tests: time now to summarise the results, taking into account other factors such as ease of use and speed.

Parts of this blog
A deep-dive review of text-to-image AI tools The 5 AI image generation tools that we will compare The 3 pre-defined tests that we will run for each tool Test 1 - photo-realism (a picture of mice being judged) Test 2 - following instructions (a treasure island map outline) Test 3 - being creative (a toy sheep as superhero) (this blog) Summing up: how our tools compare for cost, speed, ease of use and quality Conclusions and recommendations

Parts of this blog

A deep-dive review of text-to-image AI tools
The 5 AI image generation tools that we will compare
The 3 pre-defined tests that we will run for each tool
Test 1 - photo-realism (a picture of mice being judged)
Test 2 - following instructions (a treasure island map outline)
Test 3 - being creative (a toy sheep as superhero) (this blog)
Summing up: how our tools compare for cost, speed, ease of use and quality
Conclusions and recommendations

Some other pages relevant to the above blogs include:

Classes in AI (Artificial Intelligence)

This blog has 0 threads

Add a new post

BLOGS BY TOPIC

BLOGS BY AUTHOR

The images generated

Winners and Losers

Head office

London

Manchester