HomeGoogle I/O 2025 Showcases Practical Applications of Generative Media
At I/O 2025, our approach to generative AI was to demonstrate its capabilities through both presentations and practical applications. We unveiled exciting updates on our latest video and image generation models—Veo 3 and Imagen 4—and broadened access to Lyria 2. We also introduced Flow, an AI filmmaking tool that enables seamless creation of cinematic clips, scenes, and consistent narratives using our most advanced generative models.
We also integrated these tools into our flagship annual event: 219 slides from the main I/O keynote were AI-generated, 48% of keynote visuals were produced using Imagen, and 80% of the videos incorporated Veo or Imagen in some form. Here’s an in-depth look at how we leveraged our own AI tools—including our prompt-writing process—to bring I/O 2025 to life:
Veo 2: Designing Speaker Title Cards with Style
As Elizabeth Reid, our VP and Head of Search, took the stage to share major Search updates, a short video played on screen showing Liz opening her hand to reveal a delicate orange origami crane, which spun and levitated just above her palm.
We used the image-to-video feature in AI Studio and Vertex AI Studio—powered by Veo 2—to produce this and other speaker introduction videos. We collected headshots from our speakers along with details about their interests and hobbies to incorporate into the prompts. Here’s the prompt we created for research scientist Jason Baldridge’s title card:
Here’s the raw output from Veo 2, enhanced with simple animations, and what the audience saw on stage:
Imagen 4 and Veo 3: Storyboarding and Producing Films
Several films shown at I/O utilized AI tools in their production. The opening film took viewers on a thrilling journey through a Western-themed town before panning up to reveal colorful balloons spelling “Welcome to I/O,” kicking off the keynote.
The production team employed various AI tools to create it. They started by using Imagen 4 to generate images for video prompts. They also collaborated with the Google DeepMind team, who used Gemini to refine their prompts, helping them find the right language to achieve the desired results. Here’s the prompt used for the first scene:
This is what they generated:
The team then incorporated this image into the Veo 3 prompt, which included directions such as:
With the images and refined prompts ready, they began producing the film using our latest Veo 3 technology (available through the Google AI Ultra plan!). They also used Veo 3 to make real-time adjustments—adding overhead shots, wider angles, and different visuals as they reviewed the output. Unlike traditional filmmaking, where reshooting scenes is often necessary, the team could iterate much faster. No coding was required: while some team members used the Colab function for code-based editing, many others relied on text-to-video prompting, describing edits and requests in natural language.
Here’s the prompt used to create one of the film’s final scenes:
Lyria RealTime: Jamming with Toro y Moi in Real Time
During the I/O pre-show, artist Toro y Moi used Lyria RealTime in a live musical set to demonstrate the model’s latest capabilities. Lyria RealTime is our interactive music generation model that lets you create, control, and perform generative music in real time. You can blend and morph instruments, sounds, genres, and more. “This is going to be a performance and an experiment,” he explained before starting. “Everything I’m playing is completely improvised—I’m jamming with the computer, and the computer is jamming with me.”
In the weeks leading up to the performance, the team provided Toro y Moi with a Lyria RealTime prototype so he could test and refine his prompts. This helped him develop a creative concept and prompts to use during the show. He created 16 sound prompts—including “chaotic conga player” and “pitch shift U.K. jungle drums”—and assigned them to knobs on a physical MIDI controller.
Running Lyria RealTime locally via a MIDI controller allowed Toro y Moi to use the model on stage and gave the audience a live view of the interface in action.
During the performance, an app built with the Lyria RealTime API and running on the MIDI controller was displayed behind Toro y Moi. The audience saw the app’s options for creating and controlling a continuous music stream—along with the prompts he used—as he layered keyboards and vocal embellishments.
Try it yourself using the Lyria RealTime API in AI Studio.
AI Studio: Creating AI-Generated Swag
We used several Gemini models in Google AI Studio—our free interface for quickly testing models and experimenting with prompts—to design this year’s I/O shirt featuring a brand-new custom logo. As the shirt’s tag describes, the creative prompt was: “The Google I/O logo melting into the ground, rainbow colors, illustration, studio lighting.” Here’s how we created it:
First, the team selected Gemini 2.5 Pro in AI Studio and defined their objective with a detailed system instruction prompt.
After setting these guidelines, they entered the creative prompt mentioned earlier. Gemini 2.5 Pro then generated a list of requirements and style ideas for the desired image outputs. For example: “Core shapes: The fundamental geometric forms of the three original shapes (the overall rectangle, the thin slash/rectangle, and the cylinder) must still be clearly recognizable and visually distinct, even with the melting effect applied to their sides. Do not distort the core structure beyond the melting paint effect.”
Once the team had these written instructions, they switched to our workhorse model, Gemini 2.0 Flash with image generation, to produce a variety of image options based on the generated list.
After extensive experimentation, they selected several final designs—including this one.
It’s worth noting that the team also tried bypassing the initial prompt rewriting with Gemini 2.5 Pro and went directly to Gemini 2.0 Flash in AI Studio. While they came close to the desired result, using the 2.5 Pro rewrite consistently delivered better outcomes with more creative detail. The result? Some seriously cool T-shirts!
Ready for a recap? Catch up on the biggest I/O 2025 announcements here, and test your knowledge with our I/O quiz.
Ollie bets privacy focus to win AI assistant race
To be genuinely helpful, an AI assistant must understand its user deeply. Ollie, a personal assistant designed for daily life, operates on the premise that this doesn’t require surrendering your data or compromising your privacy.While certain enterpr
How AI LIVE: London Will Explore AI & Industrial Automation
The summit will convene C-suite executives from around the globe to address pressing challenges in global industries, ranging from AI-driven disruption to economic volatility.AI LIVE: The London Summit will gather over 2,000 international leaders und
Anthropic Enters AI Legal Tech Market as Competition Intensifies
Anthropic unveiled a suite of new chatbot capabilities on Tuesday, aimed at delivering automated support to legal practices. These enhancements expand upon Claude for Legal, the firm-specific platform introduced earlier this year, by adding specializ
Related Special Topic Recommendations
Text-to-speech
Best AI Text to Speech Tools for Online Courses
2026 Latest Best Top-rated AI Text to Speech Tools for Online Courses are curated by XIX.AI based on rigorous real-world tests and weekly updated rankings. These powerful tools help creators deliver crystal-clear audio content effortlessly, boosting writing efficiency and streamlining course production. Check out the free vs paid comparison to find your perfect fit. Explore now to unlock your AI edge in online education.
10 tools
xix.ai
writing
AI Blog Title Tools for Higher Click Through Rates
2026 Latest Best Top-Rated AI Blog Title Tools for Higher Click Through Rates! XIX.AI has carefully curated a powerful, game-changing collection of top tools that go through rigorous real-world tests. You’ll find a free vs paid comparison, weekly updated rankings, and detailed insights to help you boost your blog’s traffic efficiently. Must-try options are highlighted to help you unlock your AI edge. Explore now!
10 tools
xix.ai
automation
Best AI Task Routing Tools for Support Workflows
2026 Latest Best Top-rated AI Task Routing Tools for Support Workflows! XIX.AI has curated a highly powerful game-changing collection of must-try solutions, all undergoing rigorous real-world tests and updated weekly. These tools streamline workflows, boost productivity, and help teams deliver faster, more efficient support. Explore now to discover your perfect tool and unlock your AI edge!
17 tools
xix.ai
Academic Research
AI Citation and Paper Summary Tools
2026 Latest Best Top-Rated AI Citation and Paper Summary Tools Curated by XIX.AI. Get powerful game-changing solutions for quick content creation, improved writing efficiency, and boosting productivity. We offer a free vs paid comparison along with real-world tests and weekly updated rankings to help you find the must-try tool that fits your needs perfectly. Explore now to Unlock your AI edge.
10 tools
xix.ai
Productivity
Best AI Productivity Tools for Daily Work
2026 Latest Best Top-Rated AI Productivity Tools for Daily Work! XIX.AI has curated a powerful, game-changing selection based on rigorous weekly updated rankings and real-world tests. You’ll find must-try options that boost writing efficiency, streamline content creation, and help you overcome daily work challenges. Get a free vs paid comparison to find the perfect fit for your needs. Explore now to unlock your AI edge!
9 tools
xix.ai
Academic Research
AI Systematic Review Tools for Research Screening
2026 Latest Best Top-Rated AI Systematic Review Tools for Research Screening are here on XIX.AI! This curated collection includes powerful, game-changing solutions that go through rigorous real-world tests to deliver accurate results. We also offer a free vs paid comparison along with weekly updated rankings to help you find the must-try option that boosts your research efficiency significantly. Explore now to unlock your AI edge in academic work!
11 tools
xix.ai
Comments (1)
0/500
![JoseDavis]()
Veo 3 et Imagen 4 semblent impressionnants, mais j'espère que ces avancées en IA générative ne se contentent pas de faire des jolies images. Qu'en est-il de l'impact environnemental de l'entraînement de ces modèles? Les présentations sont cool, mais je veux aussi voir une vraie réflexion éthique derrière. 😅
At I/O 2025, our approach to generative AI was to demonstrate its capabilities through both presentations and practical applications. We unveiled exciting updates on our latest video and image generation models—Veo 3 and Imagen 4—and broadened access to Lyria 2. We also introduced Flow, an AI filmmaking tool that enables seamless creation of cinematic clips, scenes, and consistent narratives using our most advanced generative models.
We also integrated these tools into our flagship annual event: 219 slides from the main I/O keynote were AI-generated, 48% of keynote visuals were produced using Imagen, and 80% of the videos incorporated Veo or Imagen in some form. Here’s an in-depth look at how we leveraged our own AI tools—including our prompt-writing process—to bring I/O 2025 to life:
Veo 2: Designing Speaker Title Cards with Style
As Elizabeth Reid, our VP and Head of Search, took the stage to share major Search updates, a short video played on screen showing Liz opening her hand to reveal a delicate orange origami crane, which spun and levitated just above her palm.
We used the image-to-video feature in AI Studio and Vertex AI Studio—powered by Veo 2—to produce this and other speaker introduction videos. We collected headshots from our speakers along with details about their interests and hobbies to incorporate into the prompts. Here’s the prompt we created for research scientist Jason Baldridge’s title card:
Here’s the raw output from Veo 2, enhanced with simple animations, and what the audience saw on stage:
Imagen 4 and Veo 3: Storyboarding and Producing Films
Several films shown at I/O utilized AI tools in their production. The opening film took viewers on a thrilling journey through a Western-themed town before panning up to reveal colorful balloons spelling “Welcome to I/O,” kicking off the keynote.
The production team employed various AI tools to create it. They started by using Imagen 4 to generate images for video prompts. They also collaborated with the Google DeepMind team, who used Gemini to refine their prompts, helping them find the right language to achieve the desired results. Here’s the prompt used for the first scene:
This is what they generated:
The team then incorporated this image into the Veo 3 prompt, which included directions such as:
With the images and refined prompts ready, they began producing the film using our latest Veo 3 technology (available through the Google AI Ultra plan!). They also used Veo 3 to make real-time adjustments—adding overhead shots, wider angles, and different visuals as they reviewed the output. Unlike traditional filmmaking, where reshooting scenes is often necessary, the team could iterate much faster. No coding was required: while some team members used the Colab function for code-based editing, many others relied on text-to-video prompting, describing edits and requests in natural language.
Here’s the prompt used to create one of the film’s final scenes:
Lyria RealTime: Jamming with Toro y Moi in Real Time
During the I/O pre-show, artist Toro y Moi used Lyria RealTime in a live musical set to demonstrate the model’s latest capabilities. Lyria RealTime is our interactive music generation model that lets you create, control, and perform generative music in real time. You can blend and morph instruments, sounds, genres, and more. “This is going to be a performance and an experiment,” he explained before starting. “Everything I’m playing is completely improvised—I’m jamming with the computer, and the computer is jamming with me.”
In the weeks leading up to the performance, the team provided Toro y Moi with a Lyria RealTime prototype so he could test and refine his prompts. This helped him develop a creative concept and prompts to use during the show. He created 16 sound prompts—including “chaotic conga player” and “pitch shift U.K. jungle drums”—and assigned them to knobs on a physical MIDI controller.
Running Lyria RealTime locally via a MIDI controller allowed Toro y Moi to use the model on stage and gave the audience a live view of the interface in action.
During the performance, an app built with the Lyria RealTime API and running on the MIDI controller was displayed behind Toro y Moi. The audience saw the app’s options for creating and controlling a continuous music stream—along with the prompts he used—as he layered keyboards and vocal embellishments.
Try it yourself using the Lyria RealTime API in AI Studio.
AI Studio: Creating AI-Generated Swag
We used several Gemini models in Google AI Studio—our free interface for quickly testing models and experimenting with prompts—to design this year’s I/O shirt featuring a brand-new custom logo. As the shirt’s tag describes, the creative prompt was: “The Google I/O logo melting into the ground, rainbow colors, illustration, studio lighting.” Here’s how we created it:
First, the team selected Gemini 2.5 Pro in AI Studio and defined their objective with a detailed system instruction prompt.
After setting these guidelines, they entered the creative prompt mentioned earlier. Gemini 2.5 Pro then generated a list of requirements and style ideas for the desired image outputs. For example: “Core shapes: The fundamental geometric forms of the three original shapes (the overall rectangle, the thin slash/rectangle, and the cylinder) must still be clearly recognizable and visually distinct, even with the melting effect applied to their sides. Do not distort the core structure beyond the melting paint effect.”
Once the team had these written instructions, they switched to our workhorse model, Gemini 2.0 Flash with image generation, to produce a variety of image options based on the generated list.
After extensive experimentation, they selected several final designs—including this one.
It’s worth noting that the team also tried bypassing the initial prompt rewriting with Gemini 2.5 Pro and went directly to Gemini 2.0 Flash in AI Studio. While they came close to the desired result, using the 2.5 Pro rewrite consistently delivered better outcomes with more creative detail. The result? Some seriously cool T-shirts!
Ready for a recap? Catch up on the biggest I/O 2025 announcements here, and test your knowledge with our I/O quiz.
Ollie bets privacy focus to win AI assistant race
To be genuinely helpful, an AI assistant must understand its user deeply. Ollie, a personal assistant designed for daily life, operates on the premise that this doesn’t require surrendering your data or compromising your privacy.While certain enterpr
How AI LIVE: London Will Explore AI & Industrial Automation
The summit will convene C-suite executives from around the globe to address pressing challenges in global industries, ranging from AI-driven disruption to economic volatility.AI LIVE: The London Summit will gather over 2,000 international leaders und
Anthropic Enters AI Legal Tech Market as Competition Intensifies
Anthropic unveiled a suite of new chatbot capabilities on Tuesday, aimed at delivering automated support to legal practices. These enhancements expand upon Claude for Legal, the firm-specific platform introduced earlier this year, by adding specializ
2026 Latest Best Top-rated AI Text to Speech Tools for Online Courses are curated by XIX.AI based on rigorous real-world tests and weekly updated rankings. These powerful tools help creators deliver crystal-clear audio content effortlessly, boosting writing efficiency and streamlining course production. Check out the free vs paid comparison to find your perfect fit. Explore now to unlock your AI edge in online education.
10 tools
xix.ai
2026 Latest Best Top-Rated AI Blog Title Tools for Higher Click Through Rates! XIX.AI has carefully curated a powerful, game-changing collection of top tools that go through rigorous real-world tests. You’ll find a free vs paid comparison, weekly updated rankings, and detailed insights to help you boost your blog’s traffic efficiently. Must-try options are highlighted to help you unlock your AI edge. Explore now!
10 tools
xix.ai
2026 Latest Best Top-rated AI Task Routing Tools for Support Workflows! XIX.AI has curated a highly powerful game-changing collection of must-try solutions, all undergoing rigorous real-world tests and updated weekly. These tools streamline workflows, boost productivity, and help teams deliver faster, more efficient support. Explore now to discover your perfect tool and unlock your AI edge!
17 tools
xix.ai
2026 Latest Best Top-Rated AI Citation and Paper Summary Tools Curated by XIX.AI. Get powerful game-changing solutions for quick content creation, improved writing efficiency, and boosting productivity. We offer a free vs paid comparison along with real-world tests and weekly updated rankings to help you find the must-try tool that fits your needs perfectly. Explore now to Unlock your AI edge.
10 tools
xix.ai
2026 Latest Best Top-Rated AI Productivity Tools for Daily Work! XIX.AI has curated a powerful, game-changing selection based on rigorous weekly updated rankings and real-world tests. You’ll find must-try options that boost writing efficiency, streamline content creation, and help you overcome daily work challenges. Get a free vs paid comparison to find the perfect fit for your needs. Explore now to unlock your AI edge!
9 tools
xix.ai
2026 Latest Best Top-Rated AI Systematic Review Tools for Research Screening are here on XIX.AI! This curated collection includes powerful, game-changing solutions that go through rigorous real-world tests to deliver accurate results. We also offer a free vs paid comparison along with weekly updated rankings to help you find the must-try option that boosts your research efficiency significantly. Explore now to unlock your AI edge in academic work!
11 tools
xix.ai
Veo 3 et Imagen 4 semblent impressionnants, mais j'espère que ces avancées en IA générative ne se contentent pas de faire des jolies images. Qu'en est-il de l'impact environnemental de l'entraînement de ces modèles? Les présentations sont cool, mais je veux aussi voir une vraie réflexion éthique derrière. 😅
