Can AI create a Moho character?

[rocky53204]

Not yet it seems, but, I invite you to submit the following prompt to chatgpt.com for a quite surprising result.
It seems chatgpt is quite familiar with Moho! Once you get an answer it will ask for other prompts... follow that rabbit hole as far as you like.

prompt submission: design a production ready, fully rigged, Moho animation, male character with the appearance of a gnome.

[SimplSam]

I took the bait.

It presented this as a visualisation idea for a Dinosaur character called Rexy.


Then, later provided this as an .svg file that could be imported into Moho.


... nuff said

[Greenlaw]

Well, I give up. Thanks, guys.

[dcr]

FWIW, Corel has a product called Vector FX which uses AI to create vector images that can be exported to SVG. That would save the step of trying to vectorize the bitmap image that most AI image generators produce. Can't say how well it works as it is Windows-only and I use Macs.

But, when you consider the licensing and ethical issues, I think you're further ahead to just draw your own characters. I think it's okay to use AI to generate character ideas and relatively rapidly generate different options and ideas that you can use for inspiration in the creation of your own characters but I'm not keen on using AI to generate the final image or character to use.

[Greenlaw]

I don't think anyone here is being serious about the topic.

Personally, I don't see how using generative AI to make art for rigging saves time, at least when the goal is to produce anything of quality or originality. And, yeah, that's not even considering ethical and other problems related to using generative AI.

A while back, I dabbled with generative AI to see if it was feasible for creating background art. In each case, I spent so much time repainting and correcting the paintings that I felt I could have done a much better job more quickly if I had designed and painted the work from scratch. Another problem was maintaining scene consistency between camera angles for what were supposedly the same locations...this was pretty much impossible. Besides that, none of the art looked anything like what I would have created myself, even after all the repainting.

So, while this was an interesting experiment, it was also a big waste of time for me.

For actual production art, I'll stick with creating it myself without gen AI, or hire a fellow human artist who knows what they're doing.

[rocky53204]

Yep, the character creation sucks.
However I thought the detailed rigging info interesting.
Interesting in that I thought Moho such a niche item that AI would "know" nothing about it.

[takuya]

Following up on @dcr's mention of Corel, CorelDRAW just released an update on September 15th featuring their new "Text to Vector AI" generator (which is free to try until September 22nd).

I found this video very helpful and easy to follow:
https://youtu.be/Owiuzhgr94Y
(Text to Vector AI is Here! From Prompt to Editable Vector in CorelDRAW 2026)

I decided to test it out myself, and the results were surprisingly good.
Unlike messy auto-tracing or typical AI-generated vectors that create a nightmare of overlapping points, it generates remarkably clean vector geometry, making cleanup easy.

What makes it especially practical for Moho is that CorelDRAW has a built-in feature to intelligently reduce/simplify nodes. By combining the AI generation with node reduction, you can export lightweight, clean SVGs that are practical and easy to rig/animate in Moho.

(Also, as a side note for @dcr and other Mac users: CorelDRAW now fully supports macOS as well as a web app version, so you don't need a Windows machine to give it a try!)

[takuya]

Hi everyone,

Following up on my previous post about CorelDRAW's new Text-to-Vector AI, I put together a practical test video showing how this workflow actually connects with Moho Pro in a real production scenario!



manual
https://sentakuclip.net/jetb/wp-content ... Manual.pdf
As discussed earlier in this thread, using generative AI to create complete character rigs from scratch is still largely impractical and often inconsistent. However, I found that when applied to **architectural assets and 2.5D background elements**, the synergy with Moho is remarkably effective.

Here is the exact workflow demonstrated in the video:
1. **3D Base in Moho:** Created a simple extruded 3D rectangle to serve as a skyscraper mockup, exported a reference PNG.
2. **Text-to-Vector in CorelDRAW:** Used the reference image with prompt keywords ("skyscraper", "facade", "windows") to generate vector variations, cleaned up extraneous paths, and exported a lightweight SVG.
3. **2.5D Rigging & Action Sync in Moho (via MeshWeaver):** Imported the SVG into Moho, bound the vector facade onto the 3D building faces using the newly updated **MeshWeaver**, and set up a 3D turntable rotation.

The most impressive part of this integration is the **action synchronization**: once the 3D building rotates, running MeshWeaver’s update locks and synchronizes the entire vector facade across all action keyframes. Even when manually editing individual window points for custom deformation, the tracking remains non-destructive and intact.

Instead of expecting AI to handle full character animation, using it as a rapid asset generator for clean vector components—and letting Moho’s rigging tools handle the perspective and motion—turns out to be a massive time-saver.

Curious to hear your thoughts on using vector AI specifically for background elements and prop assets!

Best regards,
takuya