logo
Film Festival showcases what artificial intelligence can do on the big screen

Film Festival showcases what artificial intelligence can do on the big screen

Independent17 hours ago

Artificial intelligence 's use in movie making is exploding. And a young film festival, now in its junior year, is showcasing what this technology can do on screen today.
The annual AI Film Festival organized by Runway, a company that specializes in AI-generated video, kicked off in New York Thursday night with ten short films from around the world making their debut on the big screen.
'Three years ago, this was such a crazy idea,' Runway CEO Cristóbal Valenzuela told the crowd. 'Today, millions of people are making billions of videos using tools we only dreamed of.'
The film festival itself has grown significantly since its 2023 debut. About 300 people submitted films when it first began, Valenzuela said, compared to about 6,000 submissions received this year.
The one and half-hour lineup stretched across a range of creative styles and ambitious themes — with Jacob Alder's ' Total Pixel Space " taking home the festival's top prize. The 9-minute and 28-second film questions how many possible images — real or not — exist in the digital space, and uses math to calculate a colossal number. A stunning series of images, ranging from the familiar life moments to those that completely bend reality, gives viewers a glimpse of what's out there.
Meanwhile, Andrew Salter's 'Jailbird," which snagged second place, chronicles a chicken's journey — from the bird's perspective — to a human prison in the United Kingdom to take part in a joint-rehabilitation program. And 'One,' a futuristic story by Ricardo Villavicencio and Edward Saatchi about interplanetary travel followed in third place.
The 10 films shown were finalists selected from thousands submitted to Runway's AI Film Festival this year. The shorts will also be shown at screenings held in Los Angeles and Paris next week.
How AI is used and executed is a factor judges evaluate when determining festival winners. But not every film entered was made entirely using AI. While submission criteria requires each movie include the use of AI-generated video, there's no set threshold, meaning some films can take a more 'mixed media' approach — such as combining live shots of actors or real-life images and sounds with AI-generated elements.
'We're trying to encourage people to explore and experiment with it,' Valenzuela said in an interview prior to Thursday's screening.
Creating a coherent film using generative AI is no easy feat. It can take a long list of directions and numerous, detailed prompts to get even a short scene to make sense and look consistent. Still, the scope of what this kind of technology can do has grown significantly since Runway's first AI Film Festival in 2023 — and Valenzuela says that's reflected in today's submissions. While there are still limits, AI-generated video is becoming more and more life-like and realistic.
Runway encourages the use of its own AI tools for films entered into its festival, but creators are also allowed to turn to other resources and tools as they put together the films — and across the industry, tools that use AI to create videos spanning from text, image and/or audio prompts have rapidly improved over recent years, while becoming increasingly available.
'The way (this technology) has lived within film and media culture, and pop culture, has really accelerated,' said Joshua Glick, an associate professor of film and electronic arts at Bard College.
He adds that Runway's film fest, which is among a handful of showcases aimed at spotlighting AI's creative capabilities, arrives as companies in this space are searching for heightened 'legitimacy and recognition' for the tools they are creating — with aims to cement partnerships in Hollywood as a result.
AI's presence in Hollywood is already far-reaching, and perhaps more expansive than many moviegoers realize. Beyond 'headline-grabbing' (and at times controversial) applications that big-budget films have done to 'de-age' actors or create eye-catching stunts, Glick notes, this technology is often incorporated in an array of post-production editing, digital touch-ups and additional behind-the-scenes work like sorting footage.
Industry executives repeatedly point to how AI can improve efficiency in the movie making process — allowing creatives to perform a task that once took hours, for example, in a matter of minutes — and foster further innovation.
Still, AI's rapid growth and adoption has also heightened anxieties around the burgeoning technology — notably its implications for workers.
The International Alliance of Theatrical Stage Employees — which represents behind-the-scenes entertainment workers in the U.S. and Canada — has 'long embraced new technologies that enhance storytelling,' Vanessa Holtgrewe, IATSE's international vice president, said in an emailed statement. 'But we've also been clear: AI must not be used to undermine workers' rights or livelihoods.'
IATSE and other unions have continued to meet with major studios and establish provisions in efforts to provide guardrails around the use of AI. The Screen Actors Guild-American Federation of Television and Radio Artists has also been vocal about AI protections for its members, a key sticking point in recent labor actions.
For Runway's AI Film Festival, Valenzuela hopes screening films that incorporate AI-generated video can showcase what's possible — and how he says this technology can help, not hurt, creatives in the work they do today.
'It's natural to fear change ... (But) it's important to understand what you can do with it," Valenzuela said. Even filmmaking, he adds, was born 'because of scientific breakthroughs that at the time were very uncomfortable for many people."

Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

Pictured: Meghan and Harry take Archie and Lilibet to Disneyland
Pictured: Meghan and Harry take Archie and Lilibet to Disneyland

Telegraph

time21 minutes ago

  • Telegraph

Pictured: Meghan and Harry take Archie and Lilibet to Disneyland

The Duke and Duchess of Sussex have marked Princess Lilibet's fourth birthday by taking their children to Disneyland. Meghan Markle, 43, shared a carefully curated glimpse into her family's 'pure joy' on social media by posting a montage of photographs and video clips of the two-day trip to the theme park in California. They included images of Prince Archie and Princess Lilibet enjoying rides and meeting Disney characters, while Prince Harry and Meghan were shown wearing Mickey Mouse-style ears. The birthday girl appeared to have received Mickey and Minnie plush toys as gifts during the holiday, while she was also treated to a towering Little Mermaid-themed cake, according to the Instagram post. The Duke and Duchess were also seen appearing to scream while riding Disneyland's Space Mountain indoor rollercoaster. In one of the video clips, Princess Lilibet is seen taking her mother's hand and jogging excitedly alongside her parents. She and her brother, six, are then taken into a room to meet a woman dressed as Elsa, a character from the popular animated film Frozen, who waves and holds the Princess's hands. The Duchess posted love-heart emojis to cover the faces of her children in every photograph. 'Thank you @disneyland for giving our family two days of pure joy!' she captioned the post. It was the fourth Instagram post the Duchess had shared in the past week to mark her daughter turning four on June 4. A throwback video posted on the Princess's birthday showed the Duchess twerking while pregnant as Prince Harry danced around her in a hospital room before their daughter's birth. Another post featured tender moments between Prince Harry and 'Daddy's little girl and favourite adventurer'. 'The sweetest bond to watch unfold,' she wrote below photographs which included one of Harry cradling the newborn Princess. Another post included black and white portraits of Meghan holding her infant daughter, as well as a more recent one of the pair hugging during a trip to the beach. 'Happy birthday to our beautiful girl!' Meghan wrote in a caption alongside two black-and-white portraits of herself with Lilibet. 'Four years ago today she came into our lives – and each day is brighter and better because of it.' In the picture, Princess Lilibet's eyes and the top half of her face can be seen, in a departure from the Duchess's usual rule of only showing the children from the back in order to preserve their privacy.

Stop AI Hallucinations : Transform Your n8n Agent into a Precision Powerhouse
Stop AI Hallucinations : Transform Your n8n Agent into a Precision Powerhouse

Geeky Gadgets

time21 minutes ago

  • Geeky Gadgets

Stop AI Hallucinations : Transform Your n8n Agent into a Precision Powerhouse

What if your AI agent could stop making things up? Imagine asking it for critical data or a precise task, only to receive a response riddled with inaccuracies or irrelevant details. These so-called 'hallucinations' are more than just a nuisance—they can derail workflows, undermine trust, and even lead to costly mistakes. But here's the good news: by fine-tuning your n8n AI agent settings, you can dramatically reduce these errors and unlock a level of performance that's both reliable and context-aware. From selecting the right chat model to configuring memory for seamless context retention, the right adjustments can transform your AI from unpredictable to indispensable. In this comprehensive guide, FuturMinds take you through the best practices and critical settings to optimize your n8n AI agents for accuracy and efficiency. Learn how to choose the perfect chat model for your needs, fine-tune parameters like sampling temperature and frequency penalties, and use tools like output parsers to ensure structured, reliable responses. Whether you're aiming for professional-grade results in technical workflows or simply want to minimize hallucinations in everyday tasks, this report will equip you with actionable insights to achieve your goals. Because when your AI agent performs at its best, so do you. n8n AI Agent Configuration Choosing the Right Chat Model The foundation of a reliable AI agent begins with selecting the most suitable chat model. Each model offers unique capabilities, and aligning your choice with your specific use case is crucial for optimal performance. Consider the following options: Advanced Reasoning: Models like Anthropic or OpenAI GPT-4 are designed for complex problem-solving and excel in tasks requiring nuanced understanding. Models like Anthropic or OpenAI GPT-4 are designed for complex problem-solving and excel in tasks requiring nuanced understanding. Cost Efficiency: Lightweight models such as Mistral are ideal for applications where budget constraints are a priority without compromising too much on functionality. Lightweight models such as Mistral are ideal for applications where budget constraints are a priority without compromising too much on functionality. Privacy Needs: Self-hosted options like Olama provide enhanced data control, making them suitable for sensitive or proprietary information. Self-hosted options like Olama provide enhanced data control, making them suitable for sensitive or proprietary information. Multimodal Tasks: For tasks involving both text and images, models like Google Gemini or OpenAI's multimodal models are highly effective. To improve efficiency, consider implementing dynamic model selection. This approach routes tasks to the most appropriate model based on the complexity and requirements of the task, making sure both cost-effectiveness and performance. Fine-Tuning AI Agent Parameters Fine-tuning parameters is a critical step in shaping your AI agent's behavior and output. Adjusting these settings can significantly enhance the agent's performance and reliability: Frequency Penalty: Increase this value to discourage repetitive responses, making sure more diverse and meaningful outputs. Increase this value to discourage repetitive responses, making sure more diverse and meaningful outputs. Sampling Temperature: Use lower values (e.g., 0.2) for factual and precise outputs, while higher values (e.g., 0.8) encourage creative and exploratory responses. Use lower values (e.g., 0.2) for factual and precise outputs, while higher values (e.g., 0.8) encourage creative and exploratory responses. Top P: Control the diversity of responses by limiting the probability distribution, which helps in generating more focused outputs. Control the diversity of responses by limiting the probability distribution, which helps in generating more focused outputs. Maximum Tokens: Set appropriate limits to balance response length and token usage, avoiding unnecessarily long or truncated outputs. For structured outputs such as JSON, combining a low sampling temperature with a well-defined system prompt ensures accuracy and consistency. This approach is particularly useful for technical applications requiring predictable and machine-readable results. Best n8n AI Agent Settings Explained Watch this video on YouTube. Stay informed about the latest in n8n AI agent configuration by exploring our other resources and articles. Configuring Memory for Context Retention Memory configuration plays a vital role in maintaining context during multi-turn conversations. Proper memory management ensures that responses remain coherent and relevant throughout the interaction. Key recommendations include: Context Window Length: Adjust this setting to retain essential information while staying within token limits, making sure the agent can reference prior exchanges effectively. Adjust this setting to retain essential information while staying within token limits, making sure the agent can reference prior exchanges effectively. Robust Memory Nodes: For production environments, use reliable options like PostgreSQL chat memory via Supabase to handle extended interactions without risking data loss or crashes. Avoid using simple memory nodes in production, as they may not provide the stability and scalability required for complex or long-running conversations. Enhancing Functionality with Tool Integration Integrating tools expands your AI agent's capabilities by allowing it to perform specific actions via APIs. This functionality is particularly useful for automating tasks and improving efficiency. Examples include: Email Management: Integrate Gmail to send, organize, and manage emails directly through the AI agent. Integrate Gmail to send, organize, and manage emails directly through the AI agent. Custom APIs: Add domain-specific tools for specialized tasks, such as retrieving financial data, generating reports, or managing inventory. To minimize hallucinations, clearly define the parameters and scope of each tool. This ensures the agent understands its limitations and uses the tools appropriately within the defined context. Optimizing System Prompts A well-crafted system prompt is essential for defining the AI agent's role, goals, and behavior. Effective prompts should include the following elements: Domain Knowledge: Specify the agent's expertise and focus areas to ensure it provides relevant and accurate responses. Specify the agent's expertise and focus areas to ensure it provides relevant and accurate responses. Formatting Rules: Provide clear instructions for structured outputs, such as JSON, tables, or bullet points, to maintain consistency. Provide clear instructions for structured outputs, such as JSON, tables, or bullet points, to maintain consistency. Safety Instructions: Include guidelines to prevent inappropriate, harmful, or biased responses, making sure ethical and responsible AI usage. Using templates for system prompts can streamline the configuration process and reduce errors, especially when deploying multiple agents across different use cases. Using Output Parsers Output parsers are invaluable for enforcing structured and predictable responses. They are particularly useful in applications requiring machine-readable outputs, such as data pipelines and automated workflows. Common types include: Structured Output Parser: Ensures responses adhere to predefined formats, such as JSON or XML, for seamless integration with other systems. Ensures responses adhere to predefined formats, such as JSON or XML, for seamless integration with other systems. Item List Output Parser: Generates clear and organized lists with specified separators, improving readability and usability. Generates clear and organized lists with specified separators, improving readability and usability. Autofixing Output Parser: Automatically corrects improperly formatted outputs, reducing the need for manual intervention. Incorporating these tools enhances the reliability and usability of your AI agent, particularly in technical and data-driven environments. Additional Settings for Enhanced Performance Fine-tuning additional settings can further improve your AI agent's reliability and adaptability. Consider the following adjustments: Iteration Limits: Set a maximum number of iterations for tool usage loops to prevent infinite cycles and optimize resource usage. Set a maximum number of iterations for tool usage loops to prevent infinite cycles and optimize resource usage. Intermediate Steps: Enable this feature to debug and audit the agent's decision-making process, providing greater transparency and control. Enable this feature to debug and audit the agent's decision-making process, providing greater transparency and control. Multimodal Configuration: Ensure the agent can handle binary image inputs for tasks involving visual data, expanding its range of applications. These settings provide greater control over the agent's behavior, making it more versatile and effective in handling diverse scenarios. Best Practices for Continuous Improvement Building and maintaining a high-performing AI agent requires ongoing monitoring, testing, and refinement. Follow these best practices to ensure optimal performance: Regularly review and adjust settings to enhance response quality, reduce token usage, and address emerging requirements. Test the agent in real-world scenarios to identify potential issues and implement necessary improvements. Align tools, configurations, and prompts with your specific use case and objectives to maximize the agent's utility and effectiveness. Consistent evaluation and optimization are essential for making sure your AI agent remains reliable, efficient, and aligned with your goals. Media Credit: FuturMinds Filed Under: AI, Guides Latest Geeky Gadgets Deals Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.

Move over Britney Spears! Addison Rae channels Britney as she performs in her underwear in NYC
Move over Britney Spears! Addison Rae channels Britney as she performs in her underwear in NYC

Daily Mail​

timean hour ago

  • Daily Mail​

Move over Britney Spears! Addison Rae channels Britney as she performs in her underwear in NYC

Addison Rae performed in her underwear at the Spotify release party at The Box in New York City on Thursday. The singer wore a nude-toned bra and underwear as she belted out her new tunes as backup dancers surrounded her on stage. Addison has served up a dreamy pop album flaunting her 'sensual and sexual' personality. The 24-year-old social media star released her long-awaited self-titled debut studio album featuring hit singles Diet Pepsi and Aquamarine. Speaking to Variety about the new tracks, she said: 'We definitely didn't reference anything making this album. It was always me trying to provoke a feeling from a song or from music. 'I'm a very sensual and sexual person. I'm very intimate with myself and my body, and everything kind of reflects that. Everything feels very personal.' Addison also shared that having her debut album produced entirely by a team of women was 'really special'. She added that working with Luka Kloser and Elvira on the record was 'beautiful and magical'. Addison said: 'I have something really special with these girls. It feels really beautiful and magical that it is just all females. 'I never set out for it to be that way, I think because it's not very common and you almost don't get that opportunity very much to work with just females in a room.' While she has been labelled the latest 'It girl' in pop, Addison admitted that she is wary of the praise. She added: 'It is obviously very complimentary. What does that even mean, really, to be the pop girl? Let's see if the songs get more popular, then they can call me a pop girl. This is my shot. I've got to go big.' Meanwhile, Addison - who dropped her debut single Obsessed in 2023 - has spoken about how TikTok was the perfect launchpad for her career. She told Zane Lowe on Apple Music 1: 'I think in the beginning, especially, and starting out, I always knew that I wanted to make music. I always knew I wanted to act. I think I just knew I wanted to perform. 'That was just something that was really obvious to me since I was a little girl. Addison continued: 'When TikTok happened, I was almost like, well, this seems like a really nice way to get myself to Los Angeles first, because I think in Louisiana there wasn't as many opportunities or like possibility, really, to pursue that profession necessarily, unless you just got really, really lucky.' Addison gained popularity with her dance videos on TikTok in 2019. And by March 2020, rapper The Kid Laroi caused a buzz when he released a song titled Addison Rae. She then made her film debut in 2021's He's All That and released Obsessed two years later.

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into the world of global news and events? Download our app today from your preferred app store and start exploring.
app-storeplay-store