Building @AssetHub_io (The Best 3D AI Workflow) // prev Co-founder & CTO of https://nitter.gq/t.co/WpZXYGdnB8 ($100m raised from Sony, Sanrio) // 🇯🇵 @PTeamd
San Francsico, CA
Joined March 2014
- Tweets148
- Following262
- Followers227
- Likes6.8K
Pinned Tweet
we are excited to share the official launch of @assethub_io !
the team worked very hard for this launch. we will keep building!!
Takuya retweeted
New 3D AI + MetaHuman Workflow for a Modular Game Character
Running in-game in Unreal Engine!
This video shows a full pipeline using @AssetHub_io to break a character concept into parts and generate each one separately.
Concept image from GPT-Image2. All part references and base meshes generated through AssetHub with Tripo 3.1 (multi-view → 3D).
After generation:
→ AI-generated full body used as the proportion guide; all parts scale-matched and assembled in ZBrush
→ MetaHuman base sculpted to match the AI-gen face and body, detailed in ZBrush. Then assembled all of other parts.
→ manual retopo in Maya (Quad Draw)
→ UV + material sets in Maya
→ baked, then textured in Substance Painter: skin, cloth, leather, gold embroidery, metal: with normals, roughness, and micro-details
→ hair groomed with XGen
AI + MetaHuman base gave us two wins: an even faster turnaround, and clean, animation-ready topology out of the box.
Drop a comment for any questions!
Takuya retweeted
New 3D AI Workflow for Modular Game Characters
Running in-game in Unreal Engine!
For game-ready characters, generating the whole model in one shot doesn't cut it. You need modular parts. Head, torso, arms, armor, accessories: all as separate meshes so you can swap, iterate, and reuse.
This video shows a full pipeline using @AssetHub_io to break a character concept into parts and generate each one separately. It auto-detected the pose, split it into parts, then generated reference images for each piece.
Concept image from Nano Banana 2. All part images and high poly meshes generated through AssetHub: Tripo 3.1 for most models, Hitem3D for a few specific parts.
After generation:
assembled in Blender
→ AI + manual retopo
→ AI UV + unwrapping in 3ds Max
→ AI texturing (Tripo / Hitem3D) + rework in Substance Painter with normals, roughness, and micro-details.
All AI functions available on AssetHub.
Rigged in Blender, then brought into Unreal Engine with a dynamic cloth sim rig. What used to take weeks is now possible in a fraction of the time.
Drop a comment for any questions!
split parts easy with @assethub_io
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.
Takuya retweeted
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.
Takuya retweeted
build modular gaming 3D with AssetHub!!
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.
Takuya retweeted
Smart! I'm guessing the reason this workflow isn't common is because of cost? Because there's no other reason you shouldn't be able to upload a whole city and have it automatically segment each object down to the smaller components.
Takuya retweeted
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.
Takuya retweeted
アセットを分解してそれぞれ生成するワークフローだと確かにそれぞれのクオリティ維持ができそう
ローモデルのトポロジーもAIだいぶ綺麗になってきたなぁ。
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.
Takuya retweeted
Mark my words: no matter how much we hate all this, we’ll all end up somewhere there, but with some % of manual polish on top of it.
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.
Takuya retweeted
これはとても気になる。
コントロールリグまでフォローできるのは強力かもしれない。
実際3D AIワークフローをテストしていて、割とまだ手間なところが見えてきたところ。
こちらのワークフローが新しい解決策になるなら、ぜひテストしてみたい。🤔
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.
Takuya retweeted
게임업계 군중씬 이걸로 뚝딱이겠네..
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.
Takuya retweeted
The @assethub_io The AssetHub workflow is surreal. The modular generation saves hours of rework.
🔥🛠️ #GameDev #3D
Takuya retweeted
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.
Takuya retweeted
Whah these two guys don't know what's coming! 🦖
Made with a bunch of tools including Kling 3.0
Crazy how we can get the characters very consistent!
First time trying to get a couple of generated shots into a storyline that makes sense. Big challenge lol!
If you see any AI shortfilm that has story, consistent character placement, spatial logic; that person has done a great job haha
Oh btw you can try making logo reveals by setting a black first frame and logo design as last frame.
Takuya retweeted
Generating flipbooks in ComfyUI. Nothing too crazy, but these little AI workflows are definitely helpful! 🐦
When I input a black frame to the FirstLastFrame node I got some decent impulse textures. using Wan 2.2 btw.
For the bird to work i had to generate between 30-60 frames and extract every 4 frames to get better wing motion.
In UEFN / Unreal Engine i'm offsetting the animation phase for every particle to get a more random result.
Takuya retweeted
From generated reference images to riding a robot raptor in Fortnite 🦖
For now mostly the same workflow, but I also used Nano Banana to get that toe claw in the image lol. Other steps: Images from Grok Imagine, Tripo for raw 3D generation, Hunyuan 3D Studio for lowpoly and UV unwrap, Trellis2 in ComfyUI for texturing and AI upscaling. Blender for cleanup, rigging and weight painting.
Splitting up the body parts helped to get a more mid-poly result. Also with better control during cleanup. The final result has 28K triangles.
Again with the awesome retargeting tools in Unreal Engine / UEFN.
I’ll be testing different AI texturing approaches soon. Some parts can get a bit wobbly at times, most notable in hard-surface objects.
Also curious if there are any upcoming weight painting tools 😄