Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation

We introduce Divot, a Diffusion-Powered Video Tokenizer, which leverages the diffusion process for self-supervised video representation learning. We posit that if a video diffusion model can effectively de-noise video clips by taking the features of a video tokenizer as the condition, then the tokenizer has successfully captured robust spatial and temporal information. Additionally, the video diffusion model inherently functions as a de-tokenizer, decoding videos from their representations. Building upon the Divot tokenizer, we present Divot-LLM through video-to-text autoregression and text-to-video generation by modeling the distributions of continuous-valued Divot features with a Gaussian Mixture Model.

All models, training code and inference code are released!

TODOs

Release the pretrained tokenizer and de-tokenizer of Divot.
Release the pretrained and instruction tuned model of Divot-LLM.
Release inference code of Divot.
Release training and inference code of Divot-LLM.
Release training code of Divot.
Release de-tokenizer adaptation training code.

Introduction

We utilize the diffusion procedure to learn a video tokenizer in a self-supervised manner for unified comprehension and generation, where the spatiotemporal representations serve as the condition of a diffusion model to de-noise video clips. Additionally, the proxy diffusion model functions as a de-tokenizer to decode realistic video clips from the video representations.

After training the the Divot tokenizer, video features from the Divot tokenizer are fed into the LLM to perform next-word prediction for video comprehension, while learnable queries are input into the LLM to model the distributions of Divot features using a Gaussian Mixture Model (GMM) for video generation. During inference, video features are sampled from the predicted GMM distribution to decode videos using the de-tokenizer.

Usage

Dependencies

Python >= 3.8 (Recommend to use Anaconda)
PyTorch >=2.1.0
NVIDIA GPU + CUDA

Installation

Clone the repo and install dependent packages

git clone https://github.com/TencentARC/Divot.git
cd Divot
pip install -r requirements.txt

Model Weights

We release the pretrained tokenizer and de-tokenizer, pre-trained and instruction-tuned Divot-LLM. Please download the checkpoints and save them under the folder ./pretrained. For example, ./pretrained/Divot_tokenizer_detokenizer.

You also need to download Mistral-7B-Instruct-v0.1 and CLIP-ViT-H-14-laion2B-s32B-b79K, and save them under the folder ./pretrained.

Inference

Video Reconstruction with Divot

python3 src/tools/eval_Divot_video_recon.py

Video Comprehension with Divot-LLM

python3 src/tools/eval_Divot_video_comp.py

Video Generation with Divot-LLM

python3 src/tools/eval_Divot_video_gen.py

Training

Pre-training

Download the checkpoints of pre-trained Mistral-7B-Instruct-v0.1 and CLIP-ViT-H-14-laion2B-s32B-b79K , and save them under the folder ./pretrained.
Prepare the training data in the format of webdataset.
Run the following script.

sh scripts/train_Divot_pretrain_comp_gen.sh

Instruction-tuning

Download the checkpoints of pre-trained Divot tokenizer and Divot-LLM in Divot, and save them under the folder ./pretrained.
Prepare the instruction data in the format of webdataset (for generation) and jsonl (for comprehension, where each line stores a dictionary used to specify the video_path, question, and answer).
Run the following script.

### For video comprehension
sh scripts/train_Divot_sft_comp.sh

### For video generation
sh scripts/train_Divot_sft_gen.sh

Inference with your own model

Obtain "pytorch_model.bin" with the following script.

cd train_output/sft_comp/checkpoint-xxxx
python3 zero_to_fp32.py . pytorch_model.bin

Merge your trained lora with the original LLM model using the following script.

python3 src/tools/merge_agent_lora_weight.py

Load your merged model in "mistral7b_merged_xxx" and and corresponding "agent" path, For example,

llm_cfg_path = 'configs/clm_models/mistral7b_merged_sft_comp.yaml'
agent_cfg_path = 'configs/clm_models/agent_7b_in64_out64_video_gmm_sft_comp.yaml'

License

Divot is licensed under the Apache License Version 2.0 for academic purpose only except for the third-party components listed in License.

Citation

If you find the work helpful, please consider citing:

@article{ge2024divot,
  title={Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation},
  author={Ge, Yuying and Li, Yizhuo and Ge, Yixiao and Shan, Ying},
  journal={arXiv preprint arXiv:2412.04432},
  year={2024}
}

Acknowledge

Our code for Divot tokenizer and de-tokenizer is built upon DynamiCrafter. Thanks for their excellent work!