---
license: apache-2.0
---
If you like our project, please give us a star ⭐ on GitHub for latest update.
## 📰 News
* **[2024.01.27]** 👀👀👀 Our [MoE-LLaVA](https://github.com/PKU-YuanGroup/MoE-LLaVA) is released! A sparse model with 3B parameters outperformed the dense model with 7B parameters.
* **[2024.01.17]** 🔥🔥🔥 Our [LanguageBind](https://github.com/PKU-YuanGroup/LanguageBind) has been accepted at ICLR 2024!
* **[2024.01.16]** 🔥🔥🔥 We reorganize the code and support LoRA fine-tuning, checking [finetune_lora.sh](scripts/v1_5/finetune_lora.sh).
* **[2023.11.30]** 🤝 Thanks to the generous contributions of the community, the [OpenXLab's demo](https://openxlab.org.cn/apps/detail/houshaowei/Video-LLaVA) is now accessible.
* **[2023.11.23]** We are training a new and powerful model.
* **[2023.11.21]** 🤝 Check out the [replicate demo](https://replicate.com/nateraw/video-llava), created by [@nateraw](https://github.com/nateraw), who has generously supported our research!
* **[2023.11.20]** 🤗 [Hugging Face demo](https://huggingface.co/spaces/LanguageBind/Video-LLaVA) and **all codes & datasets** are available now! Welcome to **watch** 👀 this repository for the latest updates.
## 😮 Highlights
Video-LLaVA exhibits remarkable interactive capabilities between images and videos, despite the absence of image-video pairs in the dataset.
### 💡 Simple baseline, learning united visual representation by alignment before projection
- With **the binding of unified visual representations to the language feature space**, we enable an LLM to perform visual reasoning capabilities on both images and videos simultaneously.
### 🔥 High performance, complementary learning with video and image
- Extensive experiments demonstrate **the complementarity of modalities**, showcasing significant superiority when compared to models specifically designed for either images or videos.
## 🤗 Demo
### Gradio Web UI
Highly recommend trying out our web demo by the following command, which incorporates all features currently supported by Video-LLaVA. We also provide [online demo](https://huggingface.co/spaces/LanguageBind/Video-LLaVA) in Huggingface Spaces.
```bash
python -m videollava.serve.gradio_web_server
```
### CLI Inference
```bash
python -m videollava.serve.cli --model-path "LanguageBind/Video-LLaVA-7B" --file "path/to/your/video.mp4" --load-4bit
```
```bash
python -m videollava.serve.cli --model-path "LanguageBind/Video-LLaVA-7B" --file "path/to/your/image.jpg" --load-4bit
```
## 🛠️ Requirements and Installation
* Python >= 3.10
* Pytorch == 2.0.1
* CUDA Version >= 11.7
* Install required packages:
```bash
git clone https://github.com/PKU-YuanGroup/Video-LLaVA
cd Video-LLaVA
conda create -n videollava python=3.10 -y
conda activate videollava
pip install --upgrade pip # enable PEP 660 support
pip install -e .
pip install -e ".[train]"
pip install flash-attn --no-build-isolation
pip install decord opencv-python git+https://github.com/facebookresearch/pytorchvideo.git@28fe037d212663c6a24f373b94cc5d478c8c1a1d
```
## 🤖 API
**We open source all codes.** If you want to load the model (e.g. ```LanguageBind/Video-LLaVA-7B```) on local, you can use the following code snippets.
### Inference for image
```python
import torch
from videollava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN
from videollava.conversation import conv_templates, SeparatorStyle
from videollava.model.builder import load_pretrained_model
from videollava.utils import disable_torch_init
from videollava.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
def main():
disable_torch_init()
image = 'videollava/serve/examples/extreme_ironing.jpg'
inp = 'What is unusual about this image?'
model_path = 'LanguageBind/Video-LLaVA-7B'
cache_dir = 'cache_dir'
device = 'cuda'
load_4bit, load_8bit = True, False
model_name = get_model_name_from_path(model_path)
tokenizer, model, processor, _ = load_pretrained_model(model_path, None, model_name, load_8bit, load_4bit, device=device, cache_dir=cache_dir)
image_processor = processor['image']
conv_mode = "llava_v1"
conv = conv_templates[conv_mode].copy()
roles = conv.roles
image_tensor = image_processor.preprocess(image, return_tensors='pt')['pixel_values']
if type(image_tensor) is list:
tensor = [image.to(model.device, dtype=torch.float16) for image in image_tensor]
else:
tensor = image_tensor.to(model.device, dtype=torch.float16)
print(f"{roles[1]}: {inp}")
inp = DEFAULT_IMAGE_TOKEN + '\n' + inp
conv.append_message(conv.roles[0], inp)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda()
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=tensor,
do_sample=True,
temperature=0.2,
max_new_tokens=1024,
use_cache=True,
stopping_criteria=[stopping_criteria])
outputs = tokenizer.decode(output_ids[0, input_ids.shape[1]:]).strip()
print(outputs)
if __name__ == '__main__':
main()
```
### Inference for video
```python
import torch
from videollava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN
from videollava.conversation import conv_templates, SeparatorStyle
from videollava.model.builder import load_pretrained_model
from videollava.utils import disable_torch_init
from videollava.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
def main():
disable_torch_init()
video = 'videollava/serve/examples/sample_demo_1.mp4'
inp = 'Why is this video funny?'
model_path = 'LanguageBind/Video-LLaVA-7B'
cache_dir = 'cache_dir'
device = 'cuda'
load_4bit, load_8bit = True, False
model_name = get_model_name_from_path(model_path)
tokenizer, model, processor, _ = load_pretrained_model(model_path, None, model_name, load_8bit, load_4bit, device=device, cache_dir=cache_dir)
video_processor = processor['video']
conv_mode = "llava_v1"
conv = conv_templates[conv_mode].copy()
roles = conv.roles
video_tensor = video_processor(video, return_tensors='pt')['pixel_values']
if type(video_tensor) is list:
tensor = [video.to(model.device, dtype=torch.float16) for video in video_tensor]
else:
tensor = video_tensor.to(model.device, dtype=torch.float16)
print(f"{roles[1]}: {inp}")
inp = ' '.join([DEFAULT_IMAGE_TOKEN] * model.get_video_tower().config.num_frames) + '\n' + inp
conv.append_message(conv.roles[0], inp)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda()
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=tensor,
do_sample=True,
temperature=0.1,
max_new_tokens=1024,
use_cache=True,
stopping_criteria=[stopping_criteria])
outputs = tokenizer.decode(output_ids[0, input_ids.shape[1]:]).strip()
print(outputs)
if __name__ == '__main__':
main()
```
## 🗝️ Training & Validating
The training & validating instruction is in [TRAIN_AND_VALIDATE.md](TRAIN_AND_VALIDATE.md).
## 👍 Acknowledgement
* [LLaVA](https://github.com/haotian-liu/LLaVA) The codebase we built upon and it is an efficient large language and vision assistant.
* [Video-ChatGPT](https://github.com/mbzuai-oryx/Video-ChatGPT) Great job contributing the evaluation code and dataset.
## 🙌 Related Projects
* [LanguageBind](https://github.com/PKU-YuanGroup/LanguageBind) An open source five modalities language-based retrieval framework.
* [Chat-UniVi](https://github.com/PKU-YuanGroup/Chat-UniVi) This framework empowers the model to efficiently utilize a limited number of visual tokens.
## 🔒 License
* The majority of this project is released under the Apache 2.0 license as found in the [LICENSE](https://github.com/PKU-YuanGroup/Video-LLaVA/blob/main/LICENSE) file.
* The service is a research preview intended for non-commercial use only, subject to the model [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation.
## ✏️ Citation
If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:.
```BibTeX
@article{lin2023video,
title={Video-LLaVA: Learning United Visual Representation by Alignment Before Projection},
author={Lin, Bin and Zhu, Bin and Ye, Yang and Ning, Munan and Jin, Peng and Yuan, Li},
journal={arXiv preprint arXiv:2311.10122},
year={2023}
}
```
```BibTeX
@article{zhu2023languagebind,
title={LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment},
author={Zhu, Bin and Lin, Bin and Ning, Munan and Yan, Yang and Cui, Jiaxi and Wang, HongFa and Pang, Yatian and Jiang, Wenhao and Zhang, Junwu and Li, Zongwei and others},
journal={arXiv preprint arXiv:2310.01852},
year={2023}
}
```
## ✨ Star History
[](https://star-history.com/#PKU-YuanGroup/Video-LLaVA&Date)
## 🤝 Contributors
