OpenGVLab/Ask-Anything
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
This project allows you to ask questions about the content of videos and get natural language answers. You input a video file and your questions, and it provides descriptive text responses about actions, objects, and events within the video. Anyone who needs to quickly understand or summarize video content, such as content analysts, researchers, or educators, would find this useful.
3,335 stars. No commits in the last 6 months.
Use this if you need to extract specific information or generate a summary from video footage by simply asking questions in plain English.
Not ideal if you primarily need precise timestamped event detection or highly detailed, frame-by-frame analysis.
Stars
3,335
Forks
268
Language
Python
License
MIT
Category
Last pushed
Jan 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/OpenGVLab/Ask-Anything"
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!
SkyworkAI/Skywork-R1V
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in...
roboflow/vision-ai-checkup
Take your LLM to the optometrist.
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