CVFeb 8, 2024

Animated Stickers: Bringing Stickers to Life with Video Diffusion

arXiv:2402.06088v12 citationsh-index: 8
Originality Incremental advance
AI Analysis

This addresses the problem of creating engaging animated content for users in digital communication, though it is incremental as it builds on existing models.

The paper tackles generating animated stickers from text prompts and static images using a video diffusion model, achieving high-quality, relevant motion in under one second for eight-frame videos.

We introduce animated stickers, a video diffusion model which generates an animation conditioned on a text prompt and static sticker image. Our model is built on top of the state-of-the-art Emu text-to-image model, with the addition of temporal layers to model motion. Due to the domain gap, i.e. differences in visual and motion style, a model which performed well on generating natural videos can no longer generate vivid videos when applied to stickers. To bridge this gap, we employ a two-stage finetuning pipeline: first with weakly in-domain data, followed by human-in-the-loop (HITL) strategy which we term ensemble-of-teachers. It distills the best qualities of multiple teachers into a smaller student model. We show that this strategy allows us to specifically target improvements to motion quality while maintaining the style from the static image. With inference optimizations, our model is able to generate an eight-frame video with high-quality, interesting, and relevant motion in under one second.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes