VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

If our project helps you, please give us a star ⭐ on GitHub to support us. 🙏🙏

💡 Some other multimodal-LLM projects from our team may interest you ✨.

VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Boqiang Zhang^*, Kehan Li^*, Zesen Cheng^*, Zhiqiang Hu^*, Yuqian Yuan^*, Guanzheng Chen^*, Sicong Leng^*, Yuming Jiang^*, Hang Zhang^*, Xin Li^*, Peng Jin, Wenqi Zhang, Fan Wang, Lidong Bing, Deli Zhao

Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
Hang Zhang, Xin Li, Lidong Bing

VCD: Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
Sicong Leng^*, Hang Zhang^*, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, Lidong Bing

The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
Sicong Leng, Yun Xing, Zesen Cheng, Yang Zhou, Hang Zhang, Xin Li, Deli Zhao, Shijian Lu, Chunyan Miao, Lidong Bing

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss
Zesen Cheng*, Hang Zhang*, Kehan Li*, Sicong Leng, Zhiqiang Hu, Fei Wu, Deli Zhao, Xin Li, Lidong Bing

demo_video.webm

📰 News

[2025.01.21] 🚀🚀 We are excited to officially launch VideoLLaMA3, featuring enhanced performance across image and video benchmarks, along with a variety of easy-to-follow inference cookbooks. Try it out today!
[2024.10.22] Release checkpoints of VideoLLaMA2.1-7B-AV. The audio_visual branch code can be seen here: https://github.com/DAMO-NLP-SG/VideoLLaMA2/tree/audio_visual.
[2024.10.15] Release checkpoints of VideoLLaMA2.1-7B-16F-Base and VideoLLaMA2.1-7B-16F.
[2024.08.14] Release checkpoints of VideoLLaMA2-72B-Base and VideoLLaMA2-72B.
[2024.07.30] Release checkpoints of VideoLLaMA2-8x7B-Base and VideoLLaMA2-8x7B.
[2024.06.25] 🔥🔥 As of Jun 25, our VideoLLaMA2-7B-16F is the Top-1 ~7B-sized VideoLLM on the MLVU Leaderboard.
[2024.06.18] 🔥🔥 As of Jun 18, our VideoLLaMA2-7B-16F is the Top-1 ~7B-sized VideoLLM on the VideoMME Leaderboard.
[2024.06.17] 👋👋 Update technical report with the latest results and the missing references. If you have works closely related to VideoLLaMA 2 but not mentioned in the paper, feel free to let us know.
[2024.06.14] 🔥🔥 Online Demo is available.
[2024.06.03] Release training, evaluation, and serving codes of VideoLLaMA 2.

🛠️ Requirements and Installation

Basic Dependencies:

Python >= 3.8
Pytorch >= 2.2.0
CUDA Version >= 11.8
transformers == 4.40.0 (for reproducing paper results)
tokenizers == 0.19.1

[Online Mode] Install required packages (better for development):

git clone https://github.com/DAMO-NLP-SG/VideoLLaMA2
cd VideoLLaMA2
pip install -r requirements.txt
pip install flash-attn==2.5.8 --no-build-isolation

[Offline Mode] Install VideoLLaMA2 as a Python package (better for direct use):

git clone https://github.com/DAMO-NLP-SG/VideoLLaMA2
cd VideoLLaMA2
pip install --upgrade pip  # enable PEP 660 support
pip install -e .
pip install flash-attn==2.5.8 --no-build-isolation

🚀 Main Results

Multi-Choice Video QA & Video Captioning

Open-Ended Video QA

Audio QA

Audio-Visual QA

🌎 Model Zoo

Vision-only Checkpoints

Model Name	Model Type	Visual Encoder	Language Decoder	# Training Frames
VideoLLaMA2-7B-Base	Base	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	8
VideoLLaMA2-7B	Chat	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	8
VideoLLaMA2-7B-16F-Base	Base	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	16
VideoLLaMA2-7B-16F	Chat	clip-vit-large-patch14-336	Mistral-7B-Instruct-v0.2	16
VideoLLaMA2-8x7B-Base	Base	clip-vit-large-patch14-336	Mixtral-8x7B-Instruct-v0.1	8
VideoLLaMA2-8x7B	Chat	clip-vit-large-patch14-336	Mixtral-8x7B-Instruct-v0.1	8
VideoLLaMA2-72B-Base	Base	clip-vit-large-patch14-336	Qwen2-72B-Instruct	8
VideoLLaMA2-72B	Chat	clip-vit-large-patch14-336	Qwen2-72B-Instruct	8
VideoLLaMA2.1-7B-16F-Base	Base	siglip-so400m-patch14-384	Qwen2-7B-Instruct	16
VideoLLaMA2.1-7B-16F	Chat	siglip-so400m-patch14-384	Qwen2-7B-Instruct	16

Audio-Visual Checkpoints

Model Name	Type	Audio Encoder	Language Decoder
VideoLLaMA2.1-7B-AV	Chat	Fine-tuned BEATs_iter3+(AS2M)(cpt2)	VideoLLaMA2.1-7B-16F

🤗 Demo

It is highly recommended to try our online demo first.

To run a video-based LLM (Large Language Model) web demonstration on your device, you will first need to ensure that you have the necessary model checkpoints prepared, followed by adhering to the steps outlined to successfully launch the demo.

Single-model Version

Launch a gradio app directly (VideoLLaMA2-7B is adopted by default):

python videollama2/serve/gradio_web_server_adhoc.py

Multiple-model Version

Launch a global controller

cd /path/to/VideoLLaMA2
python -m videollama2.serve.controller --host 0.0.0.0 --port 10000

Launch a gradio webserver

python -m videollama2.serve.gradio_web_server --controller http://localhost:10000 --model-list-mode reload

Launch one or multiple model workers

#  export HF_ENDPOINT=https://hf-mirror.com  # If you are unable to access Hugging Face, try to uncomment this line.
python -m videollama2.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model-path /PATH/TO/MODEL1
python -m videollama2.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40001 --worker http://localhost:40001 --model-path /PATH/TO/MODEL2
python -m videollama2.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40002 --worker http://localhost:40002 --model-path /PATH/TO/MODEL3
...

🗝️ Training & Evaluation

Quick Start

To facilitate further development on top of our codebase, we provide a quick-start guide on how to train a customized VideoLLaMA2 with VideoLLaVA dataset and evaluate the trained model on the mainstream video-llm benchmarks.

Training Data Structure:

VideoLLaMA2
├── datasets
│   ├── videollava_pt
|   |   ├── llava_image/ # Available at: https://pan.baidu.com/s/17GYcE69FcJjjUM0e4Gad2w?pwd=9ga3 or https://drive.google.com/drive/folders/1QmFj2FcMAoWNCUyiUtdcW0-IOhLbOBcf?usp=drive_link
|   |   ├── valley/      # Available at: https://pan.baidu.com/s/1jluOimE7mmihEBfnpwwCew?pwd=jyjz or https://drive.google.com/drive/folders/1QmFj2FcMAoWNCUyiUtdcW0-IOhLbOBcf?usp=drive_link
|   |   └── valley_llavaimage.json # Available at: https://drive.google.com/file/d/1zGRyVSUMoczGq6cjQFmT0prH67bu2wXD/view, including 703K video-text and 558K image-text pairs
│   ├── videollava_sft
|   |   ├── llava_image_tune/  # Available at: https://pan.baidu.com/s/1l-jT6t_DlN5DTklwArsqGw?pwd=o6ko
|   |   ├── videochatgpt_tune/ # Available at: https://pan.baidu.com/s/10hJ_U7wVmYTUo75YHc_n8g?pwd=g1hf
|   |   └── videochatgpt_llavaimage_tune.json # Available at: https://drive.google.com/file/d/1zGRyVSUMoczGq6cjQFmT0prH67bu2wXD/view, including 100K video-centric, 625K image-centric and 40K text-only conversations

Command:

# VideoLLaMA2-vllava pretraining
bash scripts/vllava/pretrain.sh
# VideoLLaMA2-vllava finetuning
bash scripts/vllava/finetune.sh

Evaluation Data Structure:

VideoLLaMA2
├── eval
│   ├── egoschema # Official website: https://github.com/egoschema/EgoSchema
|   |   ├── good_clips_git/ # Available at: https://drive.google.com/drive/folders/1SS0VVz8rML1e5gWq7D7VtP1oxE2UtmhQ
|   |   └── questions.json  # Available at: https://github.com/egoschema/EgoSchema/blob/main/questions.json
│   ├── mvbench # Official website: https://huggingface.co/datasets/OpenGVLab/MVBench
|   |   ├── video/
|   |   |   ├── clever/
|   |   |   └── ...
|   |   └── json/
|   |   |   ├── action_antonym.json
|   |   |   └── ...
│   ├── perception_test_mcqa # Official website: https://huggingface.co/datasets/OpenGVLab/MVBench
|   |   ├── videos/ # Available at: https://storage.googleapis.com/dm-perception-test/zip_data/test_videos.zip
|   |   └── mc_question_test.json # Download from https://storage.googleapis.com/dm-perception-test/zip_data/mc_question_test_annotations.zip
│   ├── videomme # Official website: https://video-mme.github.io/home_page.html#leaderboard
|   |   ├── test-00000-of-00001.parquet
|   |   ├── videos/
|   |   └── subtitles/
│   ├── Activitynet_Zero_Shot_QA # Official website: https://github.com/MILVLG/activitynet-qa
|   |   ├── all_test/   # Available at: https://mbzuaiac-my.sharepoint.com/:u:/g/personal/hanoona_bangalath_mbzuai_ac_ae/EatOpE7j68tLm2XAd0u6b8ABGGdVAwLMN6rqlDGM_DwhVA?e=90WIuW
|   |   ├── test_q.json # Available at: https://github.com/MILVLG/activitynet-qa/tree/master/dataset
|   |   └── test_a.json # Available at: https://github.com/MILVLG/activitynet-qa/tree/master/dataset
│   ├── MSVD_Zero_Shot_QA # Official website: https://github.com/xudejing/video-question-answering
|   |   ├── videos/
|   |   ├── test_q.json
|   |   └── test_a.json
│   ├── videochatgpt_gen # Official website: https://github.com/mbzuai-oryx/Video-ChatGPT/tree/main/quantitative_evaluation
|   |   ├── Test_Videos/ # Available at: https://mbzuaiac-my.sharepoint.com/:u:/g/personal/hanoona_bangalath_mbzuai_ac_ae/EatOpE7j68tLm2XAd0u6b8ABGGdVAwLMN6rqlDGM_DwhVA?e=90WIuW
|   |   ├── Test_Human_Annotated_Captions/ # Available at: https://mbzuaiac-my.sharepoint.com/personal/hanoona_bangalath_mbzuai_ac_ae/_layouts/15/onedrive.aspx?id=%2Fpersonal%2Fhanoona%5Fbangalath%5Fmbzuai%5Fac%5Fae%2FDocuments%2FVideo%2DChatGPT%2FData%5FCode%5FModel%5FRelease%2FQuantitative%5FEvaluation%2Fbenchamarking%2FTest%5FHuman%5FAnnotated%5FCaptions%2Ezip&parent=%2Fpersonal%2Fhanoona%5Fbangalath%5Fmbzuai%5Fac%5Fae%2FDocuments%2FVideo%2DChatGPT%2FData%5FCode%5FModel%5FRelease%2FQuantitative%5FEvaluation%2Fbenchamarking&ga=1
|   |   ├── generic_qa.json     # These three json files available at: https://mbzuaiac-my.sharepoint.com/personal/hanoona_bangalath_mbzuai_ac_ae/_layouts/15/onedrive.aspx?id=%2Fpersonal%2Fhanoona%5Fbangalath%5Fmbzuai%5Fac%5Fae%2FDocuments%2FVideo%2DChatGPT%2FData%5FCode%5FModel%5FRelease%2FQuantitative%5FEvaluation%2Fbenchamarking%2FBenchmarking%5FQA&ga=1
|   |   ├── temporal_qa.json
|   |   └── consistency_qa.json

Command:

# mvbench evaluation
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash scripts/eval/eval_video_qa_mvbench.sh
# activitynet-qa evaluation (need to set azure openai key/endpoint/deployname)
CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash scripts/eval/eval_video_qa_mvbench.sh

Data Format

If you want to train a video-llm on your data, you need to follow the procedures below to prepare the video/image sft data:

Suppose your data structure is like:

VideoLLaMA2
├── datasets
│   ├── custom_sft
│   |   ├── images
│   |   ├── videos
|   |   └── custom.json

Then you should re-organize the annotated video/image sft data according to the following format:

"[ { "id": 0, "video": "images/xxx.jpg", "conversations": [ { "from": "human", "value": " \nWhat are the colors of the bus in the image?" }, { "from": "gpt", "value": "The bus in the image is white and red." }, ... ], } { "id": 1, "video": "videos/xxx.mp4", "conversations": [ { "from": "human", "value": "