gen‑ai.news
← Back
Video

The future of Hollywood isn’t feeding prompts into vanilla gen AI models

The future of Hollywood isn’t feeding prompts into vanilla gen AI models

The conversation around generative AI in Hollywood has largely outpaced the reality. Most commercially available video models still produce short, visually inconsistent clips, and several high-profile studio-AI partnerships have quietly fallen apart. The result has been a lot of short-form content that few would call compelling filmmaking.

"Dear Upstairs Neighbors," a short film showcased at Tribeca 2026, represents a more considered path. Rather than feeding prompts into general-purpose models, the production team worked with Google DeepMind to train custom versions of Veo and Imagen on purpose-built concept art created specifically for the project. That distinction matters - a custom-trained model can learn the specific visual language, character design, and aesthetic consistency that a production requires, whereas a generic model has no knowledge of the world being built.

This approach is more resource-intensive and requires a closer working relationship with an AI provider, which immediately raises questions about who can realistically pursue it. Independent filmmakers without access to Google DeepMind partnerships are unlikely to replicate this pipeline in the near term. But it does demonstrate that the visual inconsistency problem plaguing most AI-generated footage is not necessarily an inherent limitation of the technology - it is, at least in part, a limitation of using models that were never trained on your specific project.

The broader takeaway for the industry is that generative AI in serious production contexts may function less like a plug-and-play tool and more like a bespoke workflow built around custom data. That shifts the conversation away from which consumer-facing model produces the best results and toward questions of data preparation, model fine-tuning, and the kind of institutional access needed to make it work. Whether that model is practical for anything beyond well-resourced productions remains an open question, but "Dear Upstairs Neighbors" at least offers a concrete example of AI-assisted filmmaking that goes beyond slop.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

No image
Video

Runway’s WorldPrompt and the Engineering of Real-Time Worlds

Runway's WorldPrompt system powers its Gen World Models 2 (GWM 2), enabling real-time generation of video and audio through persistent context and timed actions. Rather than producing discrete clips, the model maintains a continuous understanding of an environment as it unfolds. The approach marks a notable shift in how world models can be steered interactively.

Gemini 3.8 Live with Live Avatar gives Google’s AI a face
Video

Gemini 3.8 Live with Live Avatar gives Google’s AI a face

Google has updated Gemini Live with an animated avatar that lip-syncs and displays facial expressions in real time during conversations. Called Live Avatar, the feature is currently limited to Gemini Enterprise customers and supports 97 languages without degrading video quality. It marks Google's latest step toward giving its AI assistant a visible, expressive presence.

No image
Video

Introducing Gemini 3.8 Live with Live Avatar

Google DeepMind has introduced Gemini 3.8 Live, an updated multimodal model paired with a new Live Avatar feature that generates an animated, talking on-screen presence during real-time conversations. The combination allows users to interact with a responsive visual agent rather than a purely voice-based interface. The release marks another step in Google's effort to make AI interactions feel more immediate and embodied.