Text to 3D model?

Hello 3D artists.

I’ve got something exciting for all the 3D artists, game developers and animators.

Since last year, text to image and other tools in the 2D creative workflow have been improving at a rapid speed.

We can create images from nothing, control the composition and characters inside these images, change the style, etc.

AI is at a stage where it can heavily support the 2D artists workflow. Where we as storytellers move from creating individual pieces to putting them together into our bigger vision. We go from building individual buildings, to organizing the city.

It’s just a matter of time before 3D workflows follow. Aaaand, I’ve found the first notable application for a 3D workflow.

It’s a text to 3D model platform called Mirage (this is a referral link every profile gets).

It’s largely based on the recent Shap-e model released by openAI, with one notable difference - a web UI + download formats.

Just like Midjourney, it’s as simple as writing text into a box and pressing generate.

It will render a 3D model, which we can download as a gif, glb, ply or png.

GLB and PLY are the big ones here, as they allow us to import this asset into 3D software and adjust it with our vision.

For me, this is the first glimpse of a 3D workflow, just as it was with Midjourney last year.

The AI output will not be exactly what we want, BUT it will do a lot of the groundwork for us. Instead of creating from scratch, we can use AI for the first 50% and finish the rest manually.

Here is an example of a generated 3D model with the prompt - a cherry blossom tree

For comparison, here is an image from the V3 version of Midjourney from September 19th 2022.

And here is the same prompt today in version 5.1, 6 months later.

The development of AI is only going to be faster. In a couple of months the 3D workflows will be at a stage that 2D workflows are now.

Adopting these workflows now will give us a big advantage when AI output becomes better.

The world of AI is as exciting as ever.

I love how many stories I’m able to create with it. Especially because it allows me to explore different formats.

Over the last 9 months I’ve been working on different projects putting together different workflows for creating 2D visuals. If you’ve been reading these mails, you’ve seen some of them.

Well, I’ve put them all into a book with detailed step by step image instructions.

It turns out, I’ve got a lot of information and knowledge to share, so I decided to spread it out in multiple books, instead of condensing it all into one mega overwhelming pack of information.

The first chapter of the 2D artists guide to AI supported workflows - Concept stage is available now.

You can use the code IMAGINATION for 50% off.

I put a lot of thought into making it a comfortable learning experience of new tools, techniques and skills.

With an open mind, I’m sure you’ll be able to extract valuable information for your own work.

I would love to hear from you as well!

If you’ve got feedback, comments, suggestions, reply to this mail and let me know.

I’m also planning to highlighting other artist’s workflows, so if you have one you would like to share, let me know!

You can stop by my website or social media and as always,

Keep creating and don’t forget to have fun. ☀