| CARVIEW |
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
Jay Zhangjie Wu1 Yixiao Ge3 Xintao Wang3 Stan Weixian Lei1 Yuchao Gu1 Yufei Shi1 Wynne Hsu2 Ying Shan3 Xiaohu Qie4 Mike Zheng Shou1
1Show Lab,2National University of Singapore
3ARC Lab,4Tencent PCG
[Paper (arXiv)] [Code (Github)] [Demo (Colab)] [Demo (Hugging Face)]
Abstract
To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting—One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we introduce Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy. At inference, we employ DDIM inversion to provide structure guidance for sampling. Extensive qualitative and numerical experiments demonstrate the remarkable ability of our method across various applications.
Method
Given a text-video pair (e.g., “a man is skiing”) as input, our method leverages the pretrained T2I diffusion models for T2V generation. During fine-tuning, we update the projection matrices in attention blocks using the standard diffusion training loss. During inference, we sample a novel video from the latent noise inverted from the input video, guided by an edited prompt (e.g., “Spider Man is surfing on the beach, cartoon style”).
Results
Pretrained T2I (Stable Diffusion)
 |
 |
 |
 |
|---|---|---|---|
"A brown bear walking on some rocks" |
some rocks → snow |
+ cartoon style |
 |
 |
 |
 |
|---|---|---|---|
"A man dressed as Santa Claus riding a motorcycle" |
Santa Claus → Spider Man |
motorcycle → sleigh car |
+ cartoon style |
 |
 |
 |
 |
|---|---|---|---|
"A car is drifting on a track with smoke coming out of it" |
car → white van |
track → desert |
Pretrained T2I (personalized)
 |
 |
 |
 |
|---|---|---|---|
"A bear is playing guitar" |
bear → a girl+ on the street |
bear → a boy+ in the coffee shop |
bear → a girl+ on the beach |
|
 |
 |
 |
|---|---|---|---|
"A bear is playing guitar" |
bear → Mr Potato Head+ made of lego |
bear → Mr Potato Head+ wearing sunglasses+ on the beach |
bear → Mr Potato Head+ in the starry night+ Van Gogh style |
|
 |
 |
 |
|---|---|---|---|
"A bear is playing guitar" |
bear → rabbit+ modern disney style |
bear → prince+ modern disney style |
bear → princess+ with sunglasses+ modern disney style |
Pretrained T2I (pose control)
Bibtex