Autoregressive Video Generation without Vector Quantization

Haoge Deng^1,4*, Ting Pan^2,4*, Haiwen Diao^3,4*, Zhengxiong Luo^4*, Yufeng Cui⁴
Huchuan Lu³, Shiguang Shan², Yonggang Qi¹, Xinlong Wang^4†

BUPT¹, ICT-CAS², DLUT³, BAAI^4
* Equal Contribution, ^† Corresponding Author

We present NOVA (NOn-Quantized Video Autoregressive Model), a model that enables autoregressive image/video generation with high efficiency. NOVA reformulates the video generation problem as non-quantized autoregressive modeling of temporal frame-by-frame prediction and spatial set-by-set prediction. NOVA generalizes well and enables diverse zero-shot generation abilities in one unified model.

🚀News

• [Dec 2024] Released 🤗 Online Demo (T2I, T2V)
• [Dec 2024] Released paper, weights, and Quick Start guide and Gradio Demo local code .

✨Hightlights

• 🔥 Novel Approach: Non-quantized video autoregressive generation.
• 🔥 State-of-the-art Performance: High efficiency with state-of-the-art t2i/t2v results.
• 🔥 Unified Modeling: Multi-task capabilities in a single unified model.

🗄️Model Zoo

See detailed description in Model Zoo

Text to Image

Model	Parameters	Resolution	Data	Weight	GenEval	DPGBench
NOVA-0.6B	0.6B	512x512	16M	🤗 HF link	0.75	81.76
NOVA-0.3B	0.3B	1024x1024	600M	🤗 HF link	0.67	80.60
NOVA-0.6B	0.6B	1024x1024	600M	🤗 HF link	0.69	82.25
NOVA-1.4B	1.4B	1024x1024	600M	🤗 HF link	0.71	83.01

Text to Video

Model	Parameters	Resolution	Data	Weight	VBench
NOVA-0.6B	0.6B	33x768x480	20M	🤗 HF link	80.12

📖Table of Contents

• 1. Installation
  • 1.1 From Source
  • 1.2 From Git
• 2. Quick Start
  • 2.1 Text to Image
  • 2.2 Text to Video
• 3. Gradio Demo
• 4. Train
• 5. Inference
• 6. Evaluation

1. Installation

1.1 From Source

Clone this repository to local disk and install:

pip install diffusers transformers accelerate imageio[ffmpeg]
git clone https://github.com/baaivision/NOVA.git
cd NOVA && pip install .

1.2 From Git

You can also install from the remote repository if you have set your Github SSH key:

pip install diffusers transformers accelerate imageio[ffmpeg]
pip install git+ssh://git@github.com/baaivision/NOVA.git

2. Quick Start

2.1 Text to Image

import torch
from diffnext.pipelines import NOVAPipeline

model_id = "BAAI/nova-d48w768-sdxl1024"
model_args = {"torch_dtype": torch.float16, "trust_remote_code": True}
pipe = NOVAPipeline.from_pretrained(model_id, **model_args)
pipe = pipe.to("cuda")

prompt = "a shiba inu wearing a beret and black turtleneck."
image = pipe(prompt).images[0]
    
image.save("shiba_inu.jpg")

2.2 Text to Video

import torch
from diffnext.pipelines import NOVAPipeline
from diffnext.utils import export_to_image, export_to_video

model_id = "BAAI/nova-d48w1024-osp480"
model_args = {"torch_dtype": torch.float16, "trust_remote_code": True}
pipe = NOVAPipeline.from_pretrained(model_id, **model_args)

# Standard device routine.
pipe = pipe.to("cuda")
# Use CPU model offload routine and expandable allocator if OOM.
# os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True"
# pipe.enable_model_cpu_offload()

# Text to Video
prompt = "Many spotted jellyfish pulsating under water."
video = pipe(prompt, max_latent_length=9).frames[0]
export_to_video(video, "jellyfish.mp4", fps=12)

# Increase AR and diffusion steps for better video quality.
video = pipe(
  prompt,
  max_latent_length=9,
  num_inference_steps=128,  # default: 64
  num_diffusion_steps=100,  # default: 25
).frames[0]
export_to_video(video, "jellyfish_v2.mp4", fps=12)

# You can also generate images from text, with the first frame as an image.
prompt = "Many spotted jellyfish pulsating under water."
image = pipe(prompt, max_latent_length=1).frames[0, 0]
export_to_image(image, "jellyfish.jpg")

3. Gradio Demo

# For text-to-image demo
python scripts/app_nova_t2i.py --model "BAAI/nova-d48w1024-sdxl1024" --device 0

# For text-to-video demo
python scripts/app_nova_t2v.py --model "BAAI/nova-d48w1024-osp480" --device 0

4. Train

• See Training Guide

5. Inference

• See Inference Guide

6. Evaluation

• See Evaluation Guide

📋Todo List

• Model zoo
• Quick Start
• Gradio Demo
• Inference guide
• Finetuning code
• Training code
• Evaluation code
• Prompt Writer
• Larger model size
• Additional downstream tasks: Image editing, Video editing, Controllable generation

Citation

If you find this repository useful, please consider giving a star ⭐ and citation 🦖:

@article{deng2024nova,
  title={Autoregressive Video Generation without Vector Quantization},
  author={Deng, Haoge and Pan, Ting and Diao, Haiwen and Luo, Zhengxiong and Cui, Yufeng and Lu, Huchuan and Shan, Shiguang and Qi, Yonggang and Wang, Xinlong},
  journal={arXiv preprint arXiv:2412.14169},
  year={2024}
}

Acknowledgement

We thank the repositories: MAE, MAR, MaskGIT, DiT, Open-Sora-Plan, CogVideo, and CodeWithGPU.

License

Code and models are licensed under Apache License 2.0.