How are you actually handling AI-generated mesh cleanup before engine handoff?

anvilinteractive · Jun 9 2026

Been integrating Meshy and Tripo outputs into UE5 pipelines for a while now and the generation step is no longer the problem — topology and textures come out reasonably usable for props and background assets. The problem is everything between export and the asset actually being in the project correctly.

My current manual steps after generation: health check for non-manifolds, remesh if tri density is too chaotic, LOD generation, rename to convention, export to correct format. On a batch of 30 props that's a half-day of babysitting that shouldn't require a human.

Curious what others are doing. Specifically:

Do you have any of this scripted or is it still manual per-asset?
Where does the process break down most often for you?
For character assets that need to deform — are you still doing full manual retopo or has anything automated that acceptably?

Not looking for tool recommendations necessarily, just want to understand if others are hitting the same wall or if I'm missing something obvious in my setup.

Eric Chadwick · Jun 9 2026

“Garbage in, garbage out” still applies to ai generated assets, in my experience. You end up polishing a turd.

And all the hidden costs are not helping… energy consumption, copyright theft, worsening job market, concentration of wealth, results looking like slop, the whole thing is a huge clusterfuck.

okidoki · 10:22AM

The almost funny things is (also in general):
When using some "result" from some AI, which in fact is some masterpiece of software developement but that's another story .. then why does one think that "some artists" are able to fix the garbage by "some script" or do have to do some manual repairs.

Isn't the problem that some AI just do not know about the whole context of specific workflow which is used in the given use case ? This is even not easy for humans. One can know a lot about any part of 3D but when working in a team then there are often some unwritten rules one has overcome.

Sometime some saying are twisted badly.. it's okay to say: "Make it exist first, you can polish it later." But there is also "concentrate on the right context" (for example "correct" proportions).. but when exchanging "polish" with "better" then one already implies that it can be bad at first. And when the proportions are "shitty" then the whole figure will be..

¯\_(ツ)_/¯

gnoop · 12:36PM

I recently needed to produce 3d mesh details from very old mesh and normal map texture where those details were flat baked, sort of closer lod and chat GPT managed to do it pretty well . It took lots of discussion whats wrong and how to interpret NM . I had to upload small pictures where the normal map is supposed to spawn vertexes and edges and where Chat did it wrong but in the and it managed to do it pretty accurate by a script executed in Blender . The whole thing took twice or even more time than if I do it myself although but as chat told my I just had to be more exact and specific in my requests for quicker result. For a next similar thing it did it almost instantly.

It works very same way for ribbon style brush alphas for example. Adobe Firefly makes something unusable whatever time you waste on this . Chat , after an hour of miss and hit discussion manages to do something okish . Still easier to do it yourself although.

Chat suggested me to use Stable Diffusion with ComfyUI instead , for more control in reaching specific things I want .

Does anyone use it? So far I am completely lost there and still get fancy weird pictures rather than exactly what I need.

As of "garbage in and out" I totally feel the approach but it's a bit of swimming against the flow IMO . Like Kodak that had been stuck to films till the very end. New times require new skills . It's always been that way . So why not share the experience instead of blaming it.

Eric Chadwick · 2:38PM

I'm all for new tooling and tech, constantly have to evaluate new things and solve problems for my day job. So I'm not a Luddite.

I think AI does have a place in tooling, but in my experience it is currently limited to assisting with filtering large datasets, and it requires a human with subject-matter expertise to verify the output.

The hidden costs are also still all compelling reasons to push back against this tech.

How are you actually handling AI-generated mesh cleanup before engine handoff?

Replies