I used Lore Machine’s generative AI to turn my story into a comic—and you can too

The narrator sits on the ground and eats breakfast with the cats. 


After greater than a 12 months in growth, Lore Machine is now out there to the general public for the primary time. For $10 a month, you may add 100,000 phrases of textual content (as much as 30,000 phrases at a time) and generate 80 pictures for brief tales, scripts, podcast transcripts, and extra. There are worth factors for energy customers too, together with an enterprise plan costing $160 a month that covers 2.24 million phrases and 1,792 pictures. The illustrations are available a spread of preset kinds, from manga to watercolor to pulp ’80s TV present.

Zac Ryder, founding father of inventive company Trendy Arts, has been utilizing an early-access model of the device since Lore Machine founder Thobey Campion first confirmed him what it might do. Ryder despatched over a script for a brief movie, and Campion used Lore Machine to show it right into a 16-page graphic novel in a single day.

“I bear in mind Thobey sharing his display. All of us had been simply utterly floored,” says Ryder. “It wasn’t a lot the picture technology side of it. It was the extent of the storytelling. From the move of the narrative to the emotion of the characters, it was spot on proper out of the gate.”

Trendy Arts is now utilizing Lore Machine to develop a fictional universe for a manga sequence based mostly on textual content written by the creator of Netflix’s Love, Dying & Robots.

The narrator encounters the person within the nook store who jokes in regards to the cat meals. 


Underneath the hood, Lore Machine is constructed from acquainted elements. A big language mannequin scans your textual content, figuring out descriptions of individuals and locations in addition to its general sentiment. A model of Steady Diffusion generates the pictures. What units it aside is how simple it’s to make use of. Between importing my story and downloading its storyboard, I clicked possibly half a dozen instances.

That makes it one in every of a brand new wave of user-friendly instruments that conceal the gorgeous energy of generative fashions behind a one-click net interface. “It’s lots of work to remain present with new AI instruments, and the interface and workflow for every device is totally different,” says Ben Palmer, CEO of the New Pc Company, a content material creation agency. “Utilizing a mega-tool with one constant UI could be very compelling. I really feel like that is the place the trade will land.”

Look! No prompts

Campion arrange the corporate behind Lore Machine two years in the past to work on a blockchain model of Wikipedia. However when he noticed how folks took to generative fashions, he switched path. Campion used the free-to-use text-to-image mannequin Midjourney to make a comic-book model of Samuel Taylor Coleridge’s The Rime of the Historical Mariner. It went viral, he says, but it surely was no enjoyable to make.

Marta confronts the narrator about their new eating regimen and affords to prepare dinner for them. 


“My spouse hated that venture,” says Campion. “I used to be as much as 4 within the morning, each evening, simply hammering away, making an attempt to get these pictures proper.” The issue was that text-to-image fashions like Midjourney generate pictures one after the other. That makes it laborious to keep up consistency between totally different pictures of the identical characters. Even locking in a particular type throughout a number of pictures might be laborious. “I ended up veering towards a trippier, summary expression,” he says.

Leave a Comment