Midjourney develops “Patchwork”, a huge canvas tool that can create by combining image generation AI and text generation AI – GIGAZINE

Midjourney, a provider of image generation AI, has launched a multiplayer world-building tool calledPatchworkannounced that it had been released. By combining a language model and an image generation model, Patchork allows multiple people to collaborate to create a single world.

Patchwork Research Preview
https://updates.midjourney.com/patchwork-research-preview/

Patchwork User Guide
https://updates.midjourney.com/patchwork-user-guide/

Patchwork allows you to develop a vague story idea into something more concrete, or collaborate with others to create a coherent setting. You can also combine images and text fragments to build visual stories like collages.

Patchwork is based on image generation AI, which allows you to create images from text. At this time, select the style you like from the generated images and select the “world” you want to create.

The shared board looks like this. You can paste the generated image or create a new image by entering text on the spot.

Also, one board can be accessed by multiple people. By sharing the images created by each member on the shared board, you will be able to match each member’s image.

In the future, Midjourney plans to make the characters and worlds created with Patchwork usable in other storytelling apps. This will make it possible to move characters in interactive stories, guide text generation by acting out story scenes with gestures, and even perform creative activities using a new LLM-based interface. is.

At the time of article creation, Patchwork was released as a research preview version,patchwork.midjourney.comYou can try it with . You will need a Midjourney account and Google login to use it. However, Midjourney notes that Patchwork is still a tool in its development stage, so there may be some glitches.