Skip to main content

Creating a 'cartoon' with GenAI - using Google's Gemini

In a previous post  https://llmapplied.blogspot.com/2024/06/creating-cartoon-with-genai.html I played with using ChatGPT4o to produce a GIF based cartoon.

In this post I will look at using Google's Gemini to go someway to do this. there will be differences though as Gemini can not
- Produce images but can find them online
-Can't combine them into a GIF so that would have to be done outside of this.

So the prompt
The language is British English. You are an experienced comic book designer and a witty writer. Create a guide to being a Computing student in Higher Education in the UK using a comic book narrative. You will use images you find on the web to do this. This should be educational and entertaining. . 

The result

A Guide to Computing Student Life

Panel 1

Student: "So, you've chosen to study computing. Brave soul!"

Panel 2

Student: "Endless coding marathons. Your new best friend: caffeine."

Panel 3

Student: "Group projects: where chaos meets collaboration."

Panel 4

Student: "All-nighters are a rite of passage. Bring snacks."

Panel 5

Student: "Nail that presentation and you'll feel like a coding rockstar."

Panel 6

Student: "Remember, breaks are essential. Your sanity depends on it."

Panel 7

Student: "The job market loves computer grads. Your future is bright!"

Panel 8

Student: "You made it! Celebrate your hard work. You earned it!"

Note: I couldn't combine the images into a GIF as I don't have access to image manipulation tools. However, you can easily combine these images into a GIF using online tools or software like Photoshop.

Would you like to focus on a specific aspect of computing student life for the next comic?




So not as consistent as the ChatGPT4o approach BUT I do like the sources being included and it is quick.




All opinions in this blog are the Author's and should not in any way be seen as reflecting the views of any organisation the Author has any association with. Twitter @scottturneruon

Comments

Popular posts from this blog

GenAI Productivity: Ideas to project proposal 1

One of the ways I use Generative AI with students is to take basic ideas for projects, usually a title, and get these tools to greater ideas and start of a project proposal. This is with all the usual caveats  Check the references (if any); It is going to be basic, so extend it. In this example I am going to use Co-pilot but the ChatGPT, etc can be used, employing a few basic prompt engineering basics: personas (who is the target audience?) and Templates (how do I want it to look?) to start this process. Example:  Project ideas for MSc Data Intelligence students (persona)  on a particular topic. The reply will include subheadings and relevant (hopefully) content for  TITLE, INTRODUCTION, PROBLEM STATEMENT. The prompt: " Taking the topic "Leveraging open-source tools to measure and present academics publications automatically from public domain data.". Give five innovative projects for a Master's level student dissertation in Data Intelligence. Each project example wi...

GenAI Productivity: Ideas to project proposal ideas from Google Scholar

From Google Scholar to Project Ideas or Using AI to Map the Future of Your Research Generated as well by Google Gemini Have you ever looked at a researcher’s Google Scholar profile and felt overwhelmed? Between the long lists of citations and dense technical titles, "connecting the dots" of a decade-long career is a massive cognitive lift. Whether you are a student hunting for a dissertation topic or a professional scouting for a collaborator, understanding the trajectory of research is harder than reading the papers themselves. In my latest experiment, I used Google Gemini to see if it could bridge this gap. I gave it a specific challenge: Analyze my own research profile and design 10 compelling project ideas for a final-year Computer Science student. The Prompt: Turning Data into Direction The secret to a good AI output is giving it a clear "anchor." By providing a URL to a live dataset (my Scholar profile), I bypassed the need to copy-paste thousands of words....

Getting multiple viewpoints with ChatGPT

Well sort of! There are approaches where we can get the generative AI to look at a problem from multiple perspectives (or personas) and bring the ideas generated, ideally informed by the others. to a final plan. One of the main strategy is called Tree of Thoughts (see here for more detail  https://www.forbes.com/sites/lanceeliot/2023/09/08/prompt-engineering-embraces-tree-of-thoughts-as-latest-new-technique-to-solve-generative-ai-toughest-problems/?sh=5ce79bdb2c8b ). The central idea is get a number of expert opinions, allow potential cross-fertilization of ideas, come up with actions or plans. Let see this action.  Scenario: Find out about the UK Government's plans on Disability support and then use Tree of Thoughts to produce some ideas for a company making disability equipment based on their website. Google's Gemini will be used. Stage 1 "UK Governments plans on Disability support ": Prompt:  Read, convert to plain text and consolidate information from the followi...