oakink/OakInk2-TaMF
[CVPR 2024] OakInk2 baseline model: Task-aware Motion Fulfillment (TaMF) via Diffusion
This project helps generate realistic sequences of human hand motions for virtual characters interacting with objects. You provide descriptions of tasks (like 'picking up a cup') and the intended path an object should take, and it outputs the corresponding hand movements. This is ideal for animators, game developers, or researchers who need to create natural-looking hand-object interactions in simulated environments.
No commits in the last 6 months.
Use this if you need to automatically generate precise and natural hand movements that complete a specific task with an object, like gripping or manipulating.
Not ideal if you need to animate full body motions or highly complex, unconstrained human-object interactions beyond basic task fulfillment.
Stars
22
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/oakink/OakInk2-TaMF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators