Using AI to Create a Title Treatment for a Sci-Fi Film

PART FIVE OF A MULTI-PART SERIES EXPLORING THE USE OF GENERATIVE AI IN KEY ART CREATION.

Hello, and welcome back to my multi-part exploration of how AI tools might be used to improve the Key Art production process.

If you need more context for what this series is about, click here.

Disclaimer: The methodologies I’m describing in this article were performed as a test to see how fully I could replicate a Key Art production process using AI and do not represent my official opinion on how all this should be done. I’m just having fun here :)

---

Last week I created some character assets in preparation for the poster design phase of my AI Key Art project.

Here are some additional items for better context about this overall project:

-The Key Art brief I originally generated: DOWNLOAD PDF

-Initial Key Art Concepts I made with MIDJOURNEY and DALL-E 3

All right!

So we’ve hit upon a step in the process that I’ve been excited for: Making a title treatment (or a logo) for the film. In case you forgot, I’m attempting to create Key Art for a fictional reboot of Stanley Kubrick’s first film, Fear and Desire.

There’s quite a few AI logo generator tools out there these days and I’m already anticipating how different types of tools might perform in this aspect. However, in order to ensure a more consistent result, I’m going to first pop into ChatGPT to get a prompt together.

(Above) Asking ChatGPT to generate a title treatment prompt for me.

And here’s what I got back:

Prompt for Logo Generation:

"Design a logo for the 2025 remake of Stanley Kubrick’s Fear and Desire, set in a futuristic lunar landscape. The logo should embody psychological tension and existential dread, featuring bold, stark typography that evokes the psychological and physical isolation of space. Use a font that is sleek and modern, with angular, sharp edges to evoke coldness and precision, yet slightly worn to reflect the harshness of the lunar environment. The font should convey a sense of corporate power, with a slight industrial feel to symbolize the ruthless corporate-driven conflict at the core of the story. Use a color palette of cold grays, whites, and metallic silvers, contrasted with deep reds and electric blues. Incorporate subtle visual elements like corporate logos or lunar landscapes to emphasize the dystopian and corporate-driven setting. The overall tone should reflect a chilling and claustrophobic atmosphere, with sharp, clean lines and a modern, industrial feel."

Now, I do think this is going to be slightly overkill or not wholly usable for some of the software I’m planning to use, but I’ll utilize as much of it as I can.

I also got ChatGPT to suggest possible base font choices for this graphic and it gave me these: Eurostile, Bank Gothic, Bureau Grot, Orbitron, Roboto Condensed Bold, Impact, Tungsten, Exo 2.

Fonts suggested to me by ChatGPT

Okay, now the fun begins. I’ve decided that I’m going to use the following tools so we can compare the results:

1. Canva's AI Logo Generator

2. Looka AI Logo Generator

3. Midjourney

4. Adobe Firefly

There are many other logo-generating tools besides these, but I thought these would illustrate the differences between these tools well.

See below for my results.

---

It's kind of the right vein, but it feels amateur. However, it DID keep the accurate spelling of the words, which about 50% of the tools I used struggled with.

---

Looka is just one of a family of tools that have been designed for the purpose of creating a logo for your brand or small business. These tools will keep the spelling of your words, yes, but stylistically aren't suitable for a film's title treatment.

---

There's the issue with spelling - as well as the fact that there's really only one style here.

---

The spelling issue again.

---

Okay, so let's stop for a second - because after trying 4 different softwares for logo-generation, I was starting to despair that I would not be able to get anything even remotely professional-looking enough for my Key Art test.

So I decided to throw one more tool into the mix. Unfortunately, it REALLY doesn't count as GenAI. However, it DOES create dynamically generated layout variations based on text that you input, so I figured that at least we're doing something that's a bit more automated than doing individually-made layout options by hand. The tool I'm talking about is WordSwag. So, using WordSwag, I was able to make the following simple options that I used both for compositional reference for Firefly and as standalone options.

Because it's following a coded template in the software, I don't get the goofy AI misspelled text, which has been a bit frustrating to deal with. I also just find that compositionally speaking, the options are cooler-looking than most of the logo-making software I've been checking out so far. I think it's because a designer created the logic for how the template is applied rather than having it be generated.

I've been battling my desire to hand-tweak the things I've been getting back as results. It's hard to fight it! But I do think it's important that you see them un-modified so that the quality of the raw results is as transparent as possible.

Therefore, I am going to constrain myself to using one of the AI-generated logos. So the final logo will be one of these, or another version that I generate later on.

Okay - that's all for today! Meet you back here next time for when we put all these assets together.

---