Papers
arxiv:2401.00896

TrailBlazer: Trajectory Control for Diffusion-Based Video Generation

Published on Dec 31, 2023
· Submitted by akhaliq on Jan 3
Authors:
,
,

Abstract

Within recent approaches to text-to-video (T2V) generation, achieving controllability in the synthesized video is often a challenge. Typically, this issue is addressed by providing low-level per-frame guidance in the form of edge maps, depth maps, or an existing video to be altered. However, the process of obtaining such guidance can be labor-intensive. This paper focuses on enhancing controllability in video synthesis by employing straightforward bounding boxes to guide the subject in various ways, all without the need for neural network training, finetuning, optimization at inference time, or the use of pre-existing videos. Our algorithm, TrailBlazer, is constructed upon a pre-trained (T2V) model, and easy to implement. The subject is directed by a bounding box through the proposed spatial and temporal attention map editing. Moreover, we introduce the concept of keyframing, allowing the subject trajectory and overall appearance to be guided by both a moving bounding box and corresponding prompts, without the need to provide a detailed mask. The method is efficient, with negligible additional computation relative to the underlying pre-trained model. Despite the simplicity of the bounding box guidance, the resulting motion is surprisingly natural, with emergent effects including perspective and movement toward the virtual camera as the box size increases.

Community

We have released our codebase and HF demo:
https://huggingface.co/spaces/hohonu-vicml/Trailblazer
https://github.com/hohonu-vicml/Trailblazer

Any comments are welcome!

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2401.00896 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2401.00896 in a dataset README.md to link it from this page.

Spaces citing this paper 1

Collections including this paper 2