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

Using an LLM to Find Themes using Thematic Analysis in an Academic Career

B rief recap In an earlier post, “Same prompt, four AIs: why answers aren’t always the same” , I looked at what happened when the same prompt was given to four different LLMs. Unsurprisingly, perhaps, the answers were not identical. That raised an interesting follow-on question: what was the prompt actually trying to do? The answer is that it was trying to support a form of thematic analysis. In that case, the object of analysis was an academic profile, including my Google Scholar profile. The version I discuss here is a modified prompt, used with Claude.ai, where I uploaded a CV and asked the system to find other appropriate public resources connected with a named person and institution. The aim was not simply to summarise the CV, but to identify visible and less visible themes across a whole career. Why use thematic analysis? Thematic analysis is widely used by academics, especially in qualitative research. Braun and Clarke’s well-known paper, Using thematic analysis in psy...

Prompt Engineering, Context Engineering and Agentic AI in Higher Education: A Short Briefing

AI in Education Prompt engineering, context engineering and agentic AI are often used interchangeably, but the literature treats them as distinct. Prompt engineering concerns crafting effective single instructions to a model (Glean, 2026). Context engineering is the broader discipline of designing and managing the entire informational environment around a model—memory, retrieval, tool outputs and conversation state—rather than a one-off instruction (Abstracta, 2026); prompt engineering operates within the context window, while context engineering determines what fills it (arXiv:2606.12422, 2026). Agentic AI describes systems that plan and execute multi-step tasks with delegated autonomy, raising organisational questions of accountability rather than purely technical ones (MIT Sloan, 2026; Palo Alto Networks, 2026). There is genuine debate about prompt engineering's durability. IEEE Spectrum (2025) reported research suggesting prompting is increasingly performed by models themse...

AI as a Mirror: Transforming Vague Student Ideas into a More Rigorous Project Agreement

The Problem: The "Generic App" and the "Time Sink" We’ve all been there: a student walks into a 1-to-1 with a vague desire to "do something with AI" or "build a fitness app." You spend 45 minutes trying to find a technical "hook" that justifies a Level 6 or Level 7 grade, only for the student to drift back into "CRUD app" territory by week three. The Philosophy: AI as a Mirror Instead of you doing the heavy lifting, this workflow uses AI as a Mirror . It reflects the student’s own skills and career goals back to them, but with the structural rigour of a virtual supervisory team. It’s not about the AI "giving" the idea; it’s about the AI forcing the student to defend and refine their own concepts until they hold water. The Framework: 3 Months of Rigour This prompt is specifically designed for intensive/conversion MSc or summer capstone projects . It assumes a tight 12-week implementation window. By forcing the AI to w...