JAMESYJL/ShapeLLM-Omni
[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding
This tool helps 3D artists, designers, and researchers generate and understand 3D content using natural language. You provide text descriptions, images, or existing 3D models as input, and it outputs new 3D models or detailed analyses of 3D shapes. Anyone involved in 3D design, virtual reality, or architectural visualization could benefit from this.
549 stars.
Use this if you need to quickly create new 3D models from text prompts or gain insights into complex 3D structures without specialized modeling software.
Not ideal if you require fine-grained, precise manual control over every vertex and polygon, as it currently focuses on AI-driven generation and understanding.
Stars
549
Forks
29
Language
Python
License
MIT
Category
Last pushed
Oct 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JAMESYJL/ShapeLLM-Omni"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice