AssetHub
46 posts
AssetHub
@assethub_io
Create a Modular 3D Model with AI
San Francisco Katılım Ocak 2026
25 Takip Edilen220 Takipçiler
AssetHub retweetledi
The vibejam is ending and you have finally achieved your lifelong dream of becoming a game dev (for a month)
Come join our AI gamedev group chat, the largest on X and connect with likeminded people!
Reply with a post of your game and i will send you an invite per DM
robot@alightinastorm
wave 4, opening the group chat for even more vibe game devs and especially pro-AI 3D designers reply with some of your work for an invite, we're over 200+ people now the aura in the gc is unmatched, every relevant person in AI x Games is in there except for you! Come, join, let's connect and build the future together
English
the best group to be in 2026
robot@alightinastorm
The vibejam is ending and you have finally achieved your lifelong dream of becoming a game dev (for a month) Come join our AI gamedev group chat, the largest on X and connect with likeminded people! Reply with a post of your game and i will send you an invite per DM
English
AssetHub retweetledi
@assethub_io Any plans for in-depth YouTube tutorials? Your three videos on there are good but I want mooooore :)
English
AssetHub retweetledi
Video AI workflow, the best @freepik
3D AI workflow, the best @assethub_io
English
this is such a great piece.
thanks for sharing @andrewpprice!
Andrew Price@andrewpprice
My full talk from BCON North America: How to Control AI with Blender. #b3d
English
AssetHub retweetledi
AssetHub retweetledi
The @assethub_io The AssetHub workflow is surreal. The modular generation saves hours of rework.
🔥🛠️ #GameDev #3D
English
AssetHub retweetledi
게임업계 군중씬 이걸로 뚝딱이겠네..
Jerome | InsaneUnreal@insaneUEFN
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.
한국어
AssetHub retweetledi
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。🤔
Jerome | InsaneUnreal@insaneUEFN
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.
日本語
AssetHub retweetledi
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.
Jerome | InsaneUnreal@insaneUEFN
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.
English
AssetHub retweetledi
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。
Jerome | InsaneUnreal@insaneUEFN
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.
日本語
AssetHub retweetledi
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.
English
@virtualfilmer Hi, we have tools to project texture with Nanobanana :）
（it's still projection based, but will update for entire Texture later ）
English
Has anyone seen any tools that can take a 3D model (with/without UVs) and 'auto generate' textures based on a prompt? Here's an example, of a real 3D model, that I opened in Maya, screenshotted, prompted in Nano Banana Pro (to fill texture), then projected using Substance 3D Painter. Any tools that do this sort of thing, but... better? [Usual disclaimer: I'm interested in AI and testing basically all tools I can find. But I am also a massive AI skeptic, and wish progress on licensed dataset-trained models was moving faster. I'm hated on both "sides". Weeeee.]
English