A former Vice exec is launching an AI platform that can visualize entire stories, scripts, or poems from the text
- Vice’s former head of publishing is launching an AI platform for the visualization of stories.
- The tool, called Lore Machine, combines text and image gen-AI capabilities to produce “storyboards.”
- Founder Thobey Campion said his aim with Lore Machine is to help writers reach more audiences easily.
Thobey Campion saw one recurring challenge in media while working for over 15 years at Vice as head of publishing, then as an independent writer, and finally getting a film deal for one of his stories: turning text into visuals was “super inefficient and super slow.”
Campion saw an opportunity to solve the story visualization challenge he’d been experiencing when generative AI became popular in 2022, and image generators like Midjourney and Stable Diffusion rose to prominence.
Lore Machine was founded by him and Moises Sanabria, the company’s chief prompt officer, as well as Kutlu Mizrak, who is in charge of natural-language processing.
Lore Machine converts text stories into images, ensuring style consistency for the various characters, locations, and recurring elements.
“To generate multiple images that feel like they’re all part of one story feels like a tug of war between a human and a machine that’s hell bent on doing its own thing,” Campion said of other AI image generators. “This consistency challenge became my holy grail.”
Users can submit their stories in any format, including poems, short stories, and screenplays, to the platform. The text is then synthesized by Lore Machine’s natural-language-processing engine to identify characters and their attributes, locations, lighting, props, and create scene summaries.
Following processing, the AI converts the textual work into an image gallery, or “storyboard,” using a dual approach that combines large language models such as ChatGPT and diffusion transformers such as Stable Diffusion.
Users can currently select from eight different “styles” for their storyboard, such as watercolor, manga, or line art.
Campion stated that the company intends to begin collaborating with artists to create customized style presets that users can purchase through a marketplace. The artists would receive 100% of the proceeds from the preset sales.
The tool uses OpenAI and Stable Diffusion, but its ultimate goal is to be “generator agnostic,” allowing users to choose between different text and image generators (for example, Stable Diffusion vs Midjourney) based on their preferences and values.
For the time being, the platform can only generate images, but Campion said the company is developing capabilities to generate animated content, as well as a “generative soundscape,” so users can create a soundtrack to accompany their stories.
Once the storyboard has been generated, users can click into each image and re-generate or modify it until they get the desired result.
Lore Machine is currently in beta and being used by screenwriters, artists, novelists, graphic novelists, and animators, according to the company, with a waitlist of over 12,000 people. So far, it’s had a successful run, collaborating on a manga with HP’s gaming division Omen, production studio Anonymous Content, and sci-fi writer Phil Gelatt.
Lore Machine’s team wants to assist writers in creating visuals that complement their stories so that they can reach a larger audience and be more involved in the extension of their work.
“In Hollywood, writers create the foundations for all entertainment and then get left out in the cold,” says Campion. “Our vision is that if writers could help shape the visual experience of their stories with Lore Machine, they could play a bigger role in a film’s production and the companion experiences.”
Campion anticipates that Lore Machine will be publicly available in early 2024.
Here’s a video of Lore Machine’s “spokesentity” explaining how the AI works in detail:
And here’s an example of a graphic novel based on Samuel T. Coleridge’s Rime of the Ancient Mariner made using Lore Machine.
