GPT-6 made GTA 6 beach house using MCP tools! Running Astra only through Blender MCP didn’t work for me, since it was mainly using primitive shapes to build the assets. Now, with @Atlas3DAI workflows and Tripo, that changed! Initially, I thought Tripo P2 would be the way to go: low-poly results straight into Blender. I tried it, but I didn’t get the results I wanted. Don’t get me wrong, P2 is great and a big improvement over P1, I just wanted more detail for this project. So I ended up using Tripo 3.1. First, I needed a good starting point. I gave Astra some concept art and YouTube links, and it generated great reference images to work with. With Atlas workflows, I used those references to generate images for all the individual parts. Using Atlas MCP, I exported them and automatically renamed everything based on the prompts. The next step was feeding the images into Atlas Batch Composer so it could run all the 3D generations in one go. I asked Astra to optimize the generated assets to either 5K or 1K triangles, depending on their form and size. After a few tests, Astra made the process faster and faster. I gave it all 70 high-poly assets and let it run. Astra then took care of the whole build. It imported the optimized assets into Blender and used the reference images to start recreating the house. I only had to give it directional feedback twice and manually rescale a few things. There were still a lot of parts, though. Each beam was a separate object, and I knew that wasn’t ideal if I wanted to export the house to UEFN or Unreal Engine. So I asked Astra to export only the unique assets. Then, using UEFN MCP, it rebuilt everything 1:1 while reusing modular parts like beams and windows. I really enjoyed watching it place all the pieces in UEFN, almost like watching a timelapse of the house being built!

I’m making a new UEFN game that’s being built 80% by AI. So I should actually say ‘directing a game? lol. Mostly just curious to see how far I can push it, but so far I like it. I’m also really happy with how Astra is implementing Verse and Scene Graph stuff. Once it understands how I want systems to be built, it keeps using that approach. No errors. I think being a generalist is becoming really useful with AI. Knowing a lot of pipelines and workflows on a base level means I can design how something should work, build the first example, and then let AI handle a lot of the repetitive work. For example, I’ll build out 1 custom weapon and define how everything should work. Then I can let Astra build 10 more. It generates the meshes, UI textures, unique sound FX, puts everything in the correct folders and follows the naming conventions. I'm still experimenting with how far I can take it, but this way is starting to click for me. I can even go outside and use Codex Remote to continue while I'm away.

got some questions about performance. Saw a max of 500 draw calls with the house fully visible exterior and interior (compared to ~200 sky only and ~300 with UEFN landscape material). all assets share 1 master material, that helps. It can be further optimized by re-baking more assets to sub 1k triangles + combining and maybe ISM. Also without screen recording it stayed at 60fps. So not perfect but i think not crazy bad.

last look at the first unarmed combat in UEFN!

1.8 million triangles to 10K with Astra + Blender in under 4 minutes! Now initially it took longer but Codex makes reusable scripts that it's improving on every iteration. I'm using Tripo 3.1 here. Tripo P2 is faster with instant low poly results but in some cases it worth the extra 4 minutes!

didn't know we're living in the future with UEFN #UE6

Yo GPT-6 Astra working with Tripo P2 models in Blender and Substance Painter is promising! Before this setup I gave Astra only a reference image from Grok Imagine and it made the robot with 147K triangles, 54 objects and 6 materials, not really usable for me. Also the end result wasn’t matching the aesthetics of the reference. Next I used Tripo P2 to create the initial 3D mesh and told GPT-6 to work with that. It fixed the wobbly wheel shape and optimized the UVs! This got interesting. Texturing has been one of the weak parts for any GenAI 3D work. I have to test some more but first impressions of Astra + Substance Painter are great! With a proper UV layout the results are very solid. You’ll be using a lot of tokens though, I think in any kind of pipeline workflow you’d better have the max plan and do some kind of hybrid approach to work together with Astra. In general super impressed, it understood everything instantly and made no mistakes. I’ll happily give some more technical tasks! Still one of the questions I have for game dev is, when will we no longer have to think about optimization. Last time I opened Unreal Engine, it still runs faster with optimized assets lol.

Something different: using AI for a complex DIY project 🛠 . For any kind of renovation I used to open a spreadsheet and start collecting items, links, prices, notes. Usually very messy at some point haha So why not try using AI this time? I thought about making a small app for it, but that will probably turn into a whole project on its own 😅 I also don't want to spread the project over a bunch of AI chats and have a chance of losing context. So I think I found a pretty nice workflow using ChatGPT, Codex and GitHub. The goal is basically to have a knowledge base for the whole project: plans, schedules, items, prices, links, videos, etc. All stored in structured files. The workflow right now: 1. I use ChatGPT to discuss anything about the project in natural language, from general building steps down to individual items I might buy. 2. When a chat is done, I ask ChatGPT to capture the useful stuff into Markdown files and put those in the project's inbox. 3. I ask Codex to read the new captures and update the actual project files. 4. Then I can browse everything locally or on GitHub and always have a reasonably clean, up-to-date view of the project. Before starting, I also had a short ChatGPT session to set up the Codex project, GitHub repo and some rules for how captures should be created and processed. Those rules live in an AGENTS.md file. So why separate ChatGPT and Codex? Mostly because the ChatGPT mobile app is great for quickly asking questions or just talking through an idea wherever I am. And my thinking is that if Codex only has to process the captures instead of all the random conversations that produced them, the actual knowledge base stays cleaner and the context stays lightweight. Also, kinda new to GitHub Mobile and I was surprised by how nice it is for reading Markdown files. Still experimenting with all of this, but so far I really like the setup. Curious if anyone has ideas to improve this workflow, or would do something completely different haha

🎥 Finally tried the new Verse camera components! 🌄 Built the entire environment using @Atlas3DAI workflows. I've been wanting to see what first-person vehicles would feel like in UEFN. The feature is still in early access, but it's awesome that you can now hook up player cameras directly through Verse. I gave Atlas a proper test, and everything you see here was built with their workflows. The Batch Composer worked great! I just set up an API workflow, throw in all the inputs, and it generates multiple assets in one go. The main workflow was created using the Atlas assistant. The setup was perfect for the initial concept and generated things like the skybox, foliage, and landscape textures. I used GPT Image 2 for reference images and mostly Tripo P1 for the 3D assets. For a few hero assets, I made a separate workflow using Tripo 3.1 with retopo and texture baking. After that, I did a bit of cleanup in Blender and created custom collision meshes for things like the ramps. Just name the collision mesh with the UCX_ prefix and UEFN / Unreal Engine automatically uses it as the collision. Now the dirt bike launches are smooth!

Let's build the next character for the team! I’m continuing to test the modular character setup in UEFN using the Metahuman Component. Works really well with custom NPCs! For this new character, I'm back to a fresh 3D workflow using @assethub_io . Still aiming for that flat/ anime style so I can go straight to the Tripo P1 model and get the low poly textured meshes to work with. Assembling and rigging are done in Blender. Again making a shape key for the eyes blinking. Because I'm going to use the same bone structure, I can re-use some Control Rig systems like the hair and eyes procedural animations. The character has 35K triangles and each accessory is about 2.5K.

- AssetHub officially launched - Using Metahuman Component as parts system in UEFN This is crazy! Just discovered I can use the Metahuman Component in UEFN as a general parts system! Perfect for modular characters. So I had to test it out. First step: character design. With GPT Image 2 I got some really solid characters to work with. These are perfect to test anime/ lowpoly models as well. @AssetHub also officially launched so I jumped on a fresh workflow to build the first one. Since I’m aiming for an anime/flat shaded style, I chose Tripo P1 to generate straight to low poly models. Results were perfect for me, UV and textured directly done. Did the main assembly in Blender. I transferred weights onto the new parts (like the jacket here) and used proportional editing to tweak vertices so everything fits together nicely. Then into UEFN / Unreal Engine: For the two-tone shadow look, I made a material that uses the sun direction as a mask. To make all the modular parts work together, I set up a blueprint with the body skeletal mesh as the base, and all the other parts attached as children. Now the really cool part: the Metahuman Component actually lets you plug in extra body parts directly. And every skeletal mesh can have its own Control Rig slot. That means you can layer procedural animations on top of your main animation setup. I used it for procedural eye blinking and hair physics. Since every part is separate, swapping variations is super easy while keeping all animations perfectly synced!

What about a 2 day version? After @andrewpprice posted about the two extremes (fully manual vs fully AI car modeling), I wanted to try a hybrid approach. Not sure if his examples were more film or game-focused, but I’m aiming for a game-ready asset. Using @AssetHub_io for the main workflow hub. Because of the canvas and part splitting tools , iterating is smooth here. Generating high poly meshes with Tripo inside AssetHub. Retopoly with Hunyuan 3D Studio. Texturing with Trellis2 in ComfyUI. Did some manual modeling for the rims since i still dont trust AI generated rims being 100% circular😄 Assembly in Blender. End result: car exterior + interior 36K tris. Wheels total still 32K hehe. I’d bake those tire detail normals onto a simple cylinder next. In UEFN / Unreal Engine i used a clear coat material to give the car some nice reflections. Is it perfect? No. retopo and texturing are still the weak spots, but that gap is closing. Would I use this in a game? 100%! (after improving the tires). If you want to try AssetHub, you can sign up and use JR1627 to skip the waitlist.

Another great Control Rig vid!

New clean 3D AI workflow Control Rig physics in UEFN! Been exploring some more hybrid AI workflows lately, and for 3D assets splitting the model into parts is kinda essential. This video shows my first test using @AssetHub_io, one of the cleanest ways i've used to keep the whole generation process organized. It auto-detected the pose in my main image and broke it down into parts, then generated images for each. From there I can just iterate on each piece separately and generate the 3D models in one workflow. AssetHub is still in closed beta atm, so let me know if you want to try it out. Main reference image came from Grok Imagine. All the part images and high poly meshes were done in AssetHub, selected Tripo 3.1 as the main model. After that I ran it through Hunyuan 3D for retopo + unwrap. Final assembly in Blender. Baked normals from high to low poly. End result: under 60K tris, 3 materials, 2K textures. Also Control Rig physics in Unreal Engine are insane. It finally validates in UEFN too, so of course I had to test it out.

built an auto-OBS recorder for UEFN and I don't know how to code in python. It automatically switch to game-mode, immersive mode and goes to frame 0. Stops OBS automatically on final frame and returns to normal viewport state. I used Codex to make the script. First took 1-2 hours preparing this UEFN-script skill. Then another 1-2 hours to make this OBS script. Although I do know Verse, I'd say knowing how to code is not needed. Just take it step by step. That initial skill setup is important though, like onboarding a new colleague. So i would take some extra time on that part. Now I want to have a MovieRenderQueue python script working in UEFN but that looks to be impossible at the moment. Something with internal GameOverride settings . Maybe someone else got it to work?

For anyone wanting to learn Unreal Engine 5. Great new series by @badxstudio !

check it out. Another great workflow to add. Always great clean vids from @JonathanWinbush