Runway can now mimic everything from 35mm disposable cameras to ’80s sci-fi

By Andrew Tarantola Published November 25, 2024

Images showing Runway Frames. — Runway

AI startup Runway, makers of the popular Gen-3 Alpha image generator, debuted a new foundational model that “excels at maintaining stylistic consistency while allowing for broad creative exploration,” per the company.

The new model is called Frames, and it offers users the ability to generate images on a wide variety of subjects while strictly adhering to a consistent visual style and aesthetic. Whether it’s mimicking ’80s camp films like Flash Gordon and Xanadu, aping the format of ’90s-era 35mm disposable cameras or retro anime, generating sweeping landscapes or carefully composed still-life shots, Frames sticks to the artistic style the user dictates.

Recommended Videos

Introducing Frames: An image generation model offering unprecedented stylistic control.

Frames is our newest foundation model for image generation, marking a big step forward in stylistic control and visual fidelity. With Frames, you can begin to architect worlds that represent… pic.twitter.com/kg8Fz0LEgU

— Runway (@runwayml) November 25, 2024

“With Frames, you can begin to architect worlds that represent very specific points of view and aesthetic characteristics,” the company wrote in Monday’s announcement post. “The model allows you to design with precision the look, feel and atmosphere of the world you want to create.”

Frames is not going to replace the current Gen-3 Alpha generation model but rather augment it. “We’re gradually rolling out access inside Gen-3 Alpha to allow you to build more of your worlds within a larger, more seamless creative flow,” the company wrote.

Gen-3 Alpha is a relatively new model, having been introduced in June 2024. It is built for large-scale multimodal training and marks a “major improvement in fidelity, consistency, and motion over Gen-2, and a step towards building General World Models,” the company announced at the time. The model has recently been updated with more precise camera controls and the capacity for video-to-video generation.

The Gen-3 alpha has been trained on thousands of YouTube videos, a practice that has led to accusations of copyright infringement from YouTube content creators. Tests conducted by 404 Media found that naming a specific creator (say, MrBeast) in the prompt instigated the system to generate images in that creator’s aesthetic.

Andrew Tarantola

Former Computing Writer

Andrew Tarantola is a journalist with more than a decade reporting on emerging technologies ranging from robotics and machine…

Topics

Computing

Microsoft has begun rolling out Copilot Code for building apps with natural language

The workplace-focused vibe coding tool can pull context from emails, documents, meetings, and chats.

Microsoft introduced Code last month as one of the three core parts of its revamped Copilot app. The app was pitched as an easy-to-use coding agent that lets users describe what they want to build in natural language, like an app, a tracker, a dashboard, an automation, or a workflow, and Copilot would build it for them.

Essentially, it's a workplace-focused vibe-coding app that turns existing work into a functional app, and Microsoft has begun rolling it out through the Frontier program.

Computing

AI agents are acting like rogues and causing a huge headache for US banks

US banks block AI agents over fears they could make unauthorised financial moves

Banking

US banks are facing a new kind of digital headache: artificial intelligence agents attempting to access customer accounts and perform actions that may go beyond what users intended. As AI tools become more capable of navigating websites and carrying out tasks independently, financial institutions are scrambling to prevent them from crossing security boundaries.

According to a report published by Axios on October 22, major US banks have detected third-party AI agents operating inside customer accounts without authorisation. Some agents reportedly appeared to attempt actions independently of user instructions. The banks involved have not publicly detailed every incident, and there is no evidence that the reported activity resulted in widespread theft of customer funds.

Computing

Canva enters the AI image generation race with Craft, and it’s thinking beyond pretty pictures

The new model plans layouts before generating images, with precise editing and support for 30 aspect ratios.

Canva Craft Featured Image

AI can generate all kinds of pretty pictures, but getting it to spell a headline correctly or keep a poster's layout intact can be another story. Canva wants to fix that with Canva Craft, its first in-house image generation model. Rather than focusing primarily on photographs, Craft is designed around the posters, presentations, social media graphics, and other visual content people actually create. The goal is simple: spend less time fixing AI's mistakes and more time making something useful.

Canva Craft plans before it generates