We're excited to announce our first challenge with Google AI!
Running through September 14, the Google AI Studio Multimodal Challenge invites you...
For further actions, you may consider blocking this person and/or reporting abuse
This is going to be epic
Can't wait to see these
Thats cool
This looks awesome
Interesting challenge, but I have a question: If I recall correctly, doesn't deploying an applet to Cloud Run require a billing account, which in turn incurs billing for the participant per run? Is the deployment part mandatory?
Hey @delaaja, great call out. Deployment is required, and Cloud Run actually has a substantial free tier, which should cover anything incurred from our judging usage. Please see this page here to see what's covered, so you can be aware while testing (pre-submission): https://cloud.google.com/run?e=48754805&hl=en#pricing
Hello mam @jess
Can I create the app in Gemini itself, then zip the code, and work on it locally using Gemini CLI? I'll be deploying the app, but not using Cloud Run, but probably Netlify/Vercel.
Would it be eligible, or will it make it ineligible for the challenge?
But for the api it will charge more
Exactly!
To be honest, I don't really understand the point of the challenge. The models that can actually generate something useful are all paid. Fine, I added billing. Now I’ve built a game, and it generates images during gameplay. The limit for the first tier is 70 requests per day. I have 4 images per run, so basically I used up all my requests just this morning and now I can’t even record a video of the game. I’ll have to wait until tomorrow.
The third model, imagen-3.0-generate-001, isn’t even available via API, it says it’s not supported. And to move to Tier 2, I apparently need to spend $300 somehow.
So overall, it’s not really clear what the organizers were expecting. I'll wait for tomorrow to record my demo videos but overall so far experience is not what I expected for the goal "Think interactive storytelling experiences, tools that process audio and visual content, platforms that understand and generate content across multiple media types."
ok, I found that gemini-2.5-flash-image-preview also can generate images - but Google AI Studio doesn't know how to use this model so in the end I fixed the code by myself.
Question about contest rules:
Hi! I have a question about the development workflow for this challenge.
My situation:
Is this approach compliant with the contest rules? The applet was created from scratch for the challenge, but I'm now developing it further outside of the AI Studio interface using Google's own development tools.
Thanks for clarification!
Anyone know when is the deadline?
Thanks for hosting the challenge.
Here is what I have come up with
Google AI Studio's Multimodal powered Disaster Recovery Assistant Tool
🤖 RapidRelief Disaster Recovery Assistant AI 2025: 5X Faster Damage Assessment & Rescue Guide ⚠️🛟
Shan F ・ Sep 14
Checkout and Looking forward to have your constructive feedback
This looks fun!!!
Exited!
Gonna be felicitating!
instead of deploy on cloud , can we share the drive link ?
dev.to/jess/comment/311pa
Seems like we need to deploy it.
Hey, this looks interesting. I'm experimenting a bit with AI studio, and initial results look promising. But as I evolve the app, I'm noticing that it's breaking things that were previously working. Should I ask it to write tests, or can I in some other way entice it to keep previous instructions into account, or ask me if anything seems contradictory?
Thinking about this a bit further, I suspect that this is a cxontext issue, where it just can't consider the whole context as I ask more and more iterations. Maybe a tool that compacts the conversation in AI studio would be good, to summarize to the agent what we already have.
is anyone have same problem with me?
the gemini studio is always show "Failed to load the app. Try reloading it." and it became endless loop just fixing nothing and not show anything.
@ben @noahbrinker
As a group participant to the competition, We would like to kindly bring to your attention that we believe the key rules about the competition is to make submission** prior to the deadline** and *should not edit the submission after the deadline until the competition results are announced.
*
However, we would like to voluntarily list submissions edited after the deadline
I hope this will be factored in judging to ensure fairness. Because, As we submitted as early on Sep 6, editing after the deadline will give undue advantage to the concerned than others.
If it's within the competition rules to allow editing after the deadline, kindly inform us so that we can also edit our submissions even after the deadline.
Thank you.
سلام بنظر بنده ۹۰درصدنمیدونن این چالش چی هست میشه زیر دیپلم توضیح بدید
نظر خودم زیر دیپلم جای نداره اینجا نداره
این چالش خاص شامل محدودیتهای زیر است:
سرزمینها و مناطق مستثنی شده:
افغانستان، بلاروس، جمهوری آفریقای مرکزی، کوبا، گینه استوایی، ایران، عراق، کوزوو، لیبی، میانمار (برمه)، کره شمالی، روسیه، سودان جنوبی، سودان، سوریه، تانزانیا، ونزوئلا، یمن،
کریمه، جمهوری خلق دونتسک (DNR)، جمهوری خلق لوهانسک (LNR).
موارد استثنای دیگر برای این چالش: کارمندان موسسات دولتی، کارمندان گوگل
کلا ما مستثنی ایم 🙂
فقط برای افراد بالای ۱۸ سال باز است
This challenge sounds really exciting! I’ve been experimenting with AI tools recently, and the multimodal side of it is what fascinates me the most how text, images, and even other inputs can come together to create something new. I’m not sure yet what direction I’ll take for this, but I’m definitely interested in joining and learning from others who participate.
Amazing
Let's gooo
I like innovation 💡 projects like this
Good luck to everyone, friends. I agree immediately, let's be creative :)
nice
When results will be announced?
Where will the winners be announced?
how can I start?
Awesome😍😍😍
Interesting!!
Great
echo 'System Report:' > report.txt
How do we get started like signup for the competition