VAST AI Research
@VastAIResearch
Followers
2K
Following
115
Media
9
Statuses
93
VAST AI Research advances the state-of-the-art in 3D + Generative AI.
San Francisco, CA
Joined November 2023
🚀 Tripo v2.5 is LIVE, and we’re thrilled to share what this leap forward means for 3D creators.
Tripo v2.5 is here! 🎉 .This major update made significant enhancements to our algorithm, enabling our creators to achieve exceptional levels of detail and geometric precision in their models. #3dmodeling #tripoai #tripo #3d #3Dprinting
1
4
25
UniRig is officially coming to #SIGGRAPH2025!. Want to learn how? Don't miss our talk:.🗓️ Wed, Aug 13 @ 2 PM.📍 West Bldg, Room 220-222. Want to see it live? Visit the @tripoai team at Booth #700 for demos and chat with the researchers. @siggraph
Thrilled to share UniRig from Tripo @tripoai @VastAIResearch: an AI model for rapid automatic 3D rigging. Rig diverse models—from humans, animals, to sci-fi creatures—in seconds! UniRig has the potential to streamline animation workflows with unparalleled accuracy & versatility.
0
3
20
RT @huanngzh: Thanks for highlighting our work! We have released.1. inference code for image to **textured 3d scene** generation in https:/….
huggingface.co
0
24
0
RT @dylan_ebert_: CVPR Highlight #2. MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation. ↔️ Segments the scene into obj….
0
15
0
RT @tripoai: ⚔️Midway Call to Arms .A wave of summoners has gathered, see if your allies are among them😈.Or better yet. forge your own….
0
4
0
RT @tripoai: Tripo Studio Beta is now live! 🥳 . With fully controllable & editable workflow, Tripo Studio will be your next 3D workspace….
0
50
0
RT @tripoai: 📢Tripo Doodle is now OPEN-SOURCED! .Accepted at #SIGGRAPHAsia 2024, we unveiled #TripoDoodle (aka TripoSG Scribble), an intera….
0
29
0
RT @yanpei_cao: Thrilled to share UniRig from Tripo @tripoai @VastAIResearch: an AI model for rapid automatic 3D rigging. Rig diverse model….
0
105
0
RT @yanpei_cao: HoloPart is here, and it’s open-source! Our generative model splits 3D shapes into complete parts, even the hidden bits. Un….
0
95
0
Big thanks to our team for pushing 3D AI forward! Explore TripoSG & TripoSF—code on GitHub, papers on arXiv, demos on HF. More releases next month—stay tuned!. TripoSG: TripoSF:
github.com
SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling - VAST-AI-Research/TripoSF
0
2
7
We're excited to release TripoSG & TripoSF—breakthrough open 3D GenAI models from Tripo @tripoai. TripoSG excels at image-to-mesh generation; TripoSF redefines high-res, complex topology with SparseFlex. Now OPEN-SOURCE!
3
15
76
RT @yanpei_cao: Big news from Tripo! We’re open-sourcing TripoSG & TripoSF—next-level 3D GenAI models for high-fidelity 3D generation. Co….
0
134
0
RT @yanpei_cao: 🎉 MIDI will be presented at #CVPR2025! We’ve dropped the code + demo for everyone to play with. Now, with our MV-Adapter,….
0
36
0
🔍 Try it yourself: .Demo:. - - Paper: Code: Project:
github.com
[ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy" - huanngzh/MV-Adapter
3
0
6
📢 Check out MV-Adapter from our team:. A versatile framework that enables text-to-multiview and image-to-multiview generation, bridging 2D and 3D content creation. Seamlessly works with custom T2I models & ControlNets.
🔥Multi-view Generation Made Easy Now🔥. Excited to present MV-Adapter, a creative productivity tool that seamlessly transfer text-to-image models to multi-view generators. [Code and demo released].Project page: Paper: Highlight>>
1
1
8
We're honored to share that TEXGen received the Best Paper Honorable Mention at #SIGGRAPHAsia2024! . A large DM to enable direct texture synthesis in UV space - a new direction for high-quality 3D content creation. Come join @andy_yx27’s presentation:.Wed 4:30-5:40pm
TEXGen: A large diffusion model learns directly in UV texture space, enabling text/image-guided texture synthesis, inpainting & completion at high resolution. 🔗 🌐 Wed 4:30-5:40pm , "Text, Texturing, and Stylization" Session.
1
3
20
Drop by Booth S-05 if you're interested in AI-powered 3D!.Whether you're curious about our technology, career opportunities, or just want to chat about the future of 3D AI - come say hi!. Wed - Fri, Booth S-05, Hall E, Tokyo Internation Forum.
0
0
2
Catch our "Tripo Doodle" demo at Real-Time Live! .See 3D AI transform sketches into 3D models instantaneously. Fri 4:00-6:00pm, "Real-Time Live!" Session.
1
0
7
TEXGen: A large diffusion model learns directly in UV texture space, enabling text/image-guided texture synthesis, inpainting & completion at high resolution. 🔗 🌐 Wed 4:30-5:40pm , "Text, Texturing, and Stylization" Session.
arxiv.org
While high-quality texture maps are essential for realistic 3D asset rendering, few studies have explored learning directly in the texture space, especially on large-scale datasets. In this work,...
1
1
6