# ILDiff: Generate Transparent Animated Stickers by Implicit Layout Distillation

arXiv: https://arxiv.org/abs/2412.20901 · HTML: https://mlsanity.com/paper/2412.20901/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 29 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack](https://mlsanity.com/paper/2309.15807/) (2023)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [On Fast Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2106.00132/) (2021)
- [KNN-Diffusion: Image Generation via Large-Scale Retrieval](https://mlsanity.com/paper/2204.02849/) (2022)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Noise Estimation for Generative Diffusion Models](https://mlsanity.com/paper/2104.02600/) (2021)
- [Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems](https://mlsanity.com/paper/2012.03448/) (2020)
- [A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming](https://mlsanity.com/paper/2404.16038/) (2024)
- [Matting Anything](https://mlsanity.com/paper/2306.05399/) (2023)
- [VMFormer: End-to-End Video Matting with Transformer](https://mlsanity.com/paper/2208.12801/) (2022)
- [Diffusion-Based Visual Art Creation: A Survey and New Perspectives](https://mlsanity.com/paper/2408.12128/) (2024)
- [VSD2M: A Large-scale Vision-language Sticker Dataset for Multi-frame Animated Sticker Generation](https://mlsanity.com/paper/2412.08259/) (2024)
- [Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression](https://mlsanity.com/paper/2311.10794/) (2023)
- [Animated Stickers: Bringing Stickers to Life with Video Diffusion](https://mlsanity.com/paper/2402.06088/) (2024)

## Built on by (most cited first, 2 of 2)

- [Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner](https://mlsanity.com/paper/2509.24979/) (2025)
- [Loopy: Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding](https://mlsanity.com/paper/2608.23090/) (2026)

## Abstract (arXiv)

High-quality animated stickers usually contain transparent channels, which are often ignored by current video generation models. To generate fine-grained animated transparency channels, existing methods can be roughly divided into video matting algorithms and diffusion-based algorithms. The methods based on video matting have poor performance in dealing with semi-open areas in stickers, while diffusion-based methods are often used to model a single image, which will lead to local flicker when modeling animated stickers. In this paper, we firstly propose an ILDiff method to generate animated transparent channels through implicit layout distillation, which solves the problems of semi-open area collapse and no consideration of temporal information in existing methods. Secondly, we create the Transparent Animated Sticker Dataset (TASD), which contains 0.32M high-quality samples with transparent channel, to provide data support for related fields. Extensive experiments demonstrate that ILDiff can produce finer and smoother transparent channels compared to other methods such as Matting Anything and Layer Diffusion. Our code and dataset will be released at link https://xiaoyuan1996.github.io.