Powered by

I’ve got a link to one of our more recent Denoised episodes below, breaking down the low budgets for the films that won big this year at the Oscars (Anora, The Brutalist, Flow).

To further hammer this point, someone on X pointed out that the $320 million budget for Netflix’s Electric State is more than the last 15 Best Picture winners combined.

Also in today’s issue, we’ve got a few updates from Google, including Conversational Image Editing. I’ve never been a fan of doing creative work with text prompts, but this looks like it could sway me, especially for rapid iteration (vibe creation?).

Plus, Gemma 3 (not related to Ms. Casey), an open-source model from Google that can run on your computer.

Joey

Google's Gemini Introduces Conversational Image Editing in AI Studio

Google has launched a multimodal image generator for Gemini that enables conversational image editing through natural language prompts. The technology, now available in Google AI Studio, allows users to create and refine images through back-and-forth conversation with the AI system.

Bilawal has a breakdown of how it works on X.

• Gemini 2.0 Flash offers native image generation capabilities through natural language prompts, making it accessible to non-technical users

• The system supports iterative refinement, allowing users to have conversational feedback loops to perfect images without starting over

• Google AI Studio now provides free access to experiment with these features, democratizing access to advanced image generation tools

• The technology maintains consistency in visual storytelling by preserving character and setting details across iterations

Gemini can process multiple data types simultaneously, including text, images, audio, and video up to 90 minutes long.

Read more to explore how production teams are already implementing Gemini's multimodal capabilities to streamline storyboarding, concept visualization, and pre-visualization workflows.

SPONSOR MESSAGE

MASV is a faster, easier way to transfer large files to anyone, anywhere in the world—with just an internet connection.

MASV now offers a new free tier offering 10GB/month of free transfers with full enterprise features, alongside pricing updates that cut storage costs by 30% and provide up to 40% savings on subscription plans.

Trusted by media and entertainment organizations across the globe, MASV plays an essential role in thousands of video workflows, giving production professionals absolute confidence in media delivery.

Unlike other file transfer services, MASV has no size limits and always delivers blazing-fast transfer speeds.

Try MASV for free.

Google's Gemma 3: AI Powerhouse that Runs on Standard Production Hardware

Google has released Gemma 3, an AI model that processes video and images efficiently on smaller hardware while outperforming many larger models.

• Massive context window: Gemma 3 features a 128,000-token context window, enabling it to process and "understand" entire scripts, storyboards, or lengthy footage metadata in a single pass

• True multimodal capabilities: The model can analyze text, images, and videos simultaneously using its SigLIP vision encoder—identifying objects, reading text within images, and responding to visual questions

• Runs on limited hardware: Unlike many advanced AI systems, Gemma 3 can operate on a single GPU or even devices like Jetson Nano, making it viable for on-location use

• Supports 140+ languages: The multilingual support enables international production teams to work across language barriers more seamlessly

Read more to explore how production companies could potentially implement Gemma 3 for real-time footage analysis, automated continuity tracking, and on-set creative decision support.

Yuzu & Mirage: Two New AI Avatar Video Creators

Add to the AI avatar bucket with HeyGen and Synthesia, we've got two new AI tools joining the mix with their own unique models.

Yuzu Labs' "Cursor for Videos" leverages AI avatars to create professional-quality videos without filming or editing.

• Users simply type a script, and the system generates customized content optimized for social media engagement.

• The technology uses machine learning and facial AI to create realistic avatars, enhancing open-source models with unique data sets for customization and realism.

Meanwhile, Mirage, described as the first UGC foundation model, allows marketers to generate talking videos of non-existent people by defining appearance, environment, and expression.

• Mirage integrates directly into Captions' Ad Studio platform, enabling users to create UGC-style video ads by simply inputting scripts and defining speaker attributes

• The technology generates videos featuring animated body language and micro-expressions, creating content that mimics the authenticity of traditional user-generated content

• Users can customize speaker appearance, environment, and emotional expression, providing unprecedented flexibility for marketers working across various campaigns

This week on Denoised: Joey and Addy discuss $10M movie budgets as the new norm, plus Manus AI and Mac Studio Ultra upgrades.

Stories, projects, and links that caught our attention from around the web:

👹 Paddington in Peru writers are bringing Critterz to life as a full-length AI-driven animated film.

👋 Vicon introduces advanced markerless motion capture, transforming workflows in film, TV, and game development.

🎨 FilmLight brings its high-end Baselight color grading tools to macOS with affordable subscription options.

📽 Go inside ILM’s industry-defining filmmaking in Light & Magic Season 2, streaming April 18 on Disney+

🚫 Miami Beach mayor moves to evict O Cinema and proposes grant withdrawal after screening Oscar-winning No Other Land, in a move drawing vast amounts of criticism and overreach of censorship.

▶️ Google’s Veo 2 Image-to-Video is now live on fal

👔 Open Job Posts

AI Architect & Technical Strategist
Machine Learning Engineer, PyTorch
Cuebric
Remote

Art Director, Generative AI - Avatars
Meta
Los Angeles, California

XR Instructor
Immxrsive - National Centre of Excellence for Immersive Tech
Ontario, Canada

AR/VR Intern
LumeXR
Kerala, India

Virtual Production Intern
Orbital Studios
Los Angeles, California

📆 Upcoming Events

March 7 to 15
2025 SXSW Conference & Festivals
Austin, TX

April 6 to 9
NAB Show Las Vegas
Las Vegas, NV

April 9 to 10
Virtual Productions Gathering 2025
Breda, Netherlands

June 5 to 8
Cine Gear Los Angeles Expo 2025
Los Angeles, CA

September 23 to 24
CFX 2025
Chattanooga, TN

View the full event calendar and submit your own events here.

Thanks for reading VP Land!

Thanks for reading VP Land!

Have a link to share or a story idea? Send it here.

Interested in reaching media industry professionals? Advertise with us.