yuanze-lin/Olympus
[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"
This project helps computer vision researchers and developers orchestrate complex image and video manipulation workflows. It takes a natural language prompt describing multiple visual tasks (like generating, editing, or creating 3D models from images) and intelligently breaks them down. The output is a sequence of actions, each routed to the appropriate computer vision function, enabling a streamlined workflow for multi-step visual content creation and analysis.
427 stars. No commits in the last 6 months.
Use this if you need to automate a series of interconnected computer vision tasks based on a single, descriptive natural language instruction.
Not ideal if your tasks are simple, single-step operations or if you require direct, low-level control over individual computer vision models without any routing or orchestration.
Stars
427
Forks
72
Language
Python
License
—
Category
Last pushed
May 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/yuanze-lin/Olympus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jingyaogong/minimind-v
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
roboflow/vision-ai-checkup
Take your LLM to the optometrist.
SkyworkAI/Skywork-R1V
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in...
zai-org/GLM-TTS
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
NExT-GPT/NExT-GPT
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model