# LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors

arXiv: https://arxiv.org/abs/2412.04460 · HTML: https://mlsanity.com/paper/2412.04460/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (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)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Implicit Style-Content Separation using B-LoRA](https://mlsanity.com/paper/2403.14572/) (2024)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Harmonizer: Learning to Perform White-Box Image and Video Harmonization](https://mlsanity.com/paper/2207.01322/) (2022)
- [MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation](https://mlsanity.com/paper/2404.02790/) (2024)
- [Matting Anything](https://mlsanity.com/paper/2306.05399/) (2023)
- [PP-Matting: High-Accuracy Natural Image Matting](https://mlsanity.com/paper/2204.09433/) (2022)
- [Alfie: Democratising RGBA Image Generation With No ](https://mlsanity.com/paper/2408.14826/) (2024)
- [Dense Pixel-to-Pixel Harmonization via Continuous Image Representation](https://mlsanity.com/paper/2303.01681/) (2023)
- [The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP](https://mlsanity.com/paper/2406.00457/) (2024)

## Built on by (most cited first, 19 of 19)

- [OmniPSD: Layered PSD Generation with Diffusion Transformer](https://mlsanity.com/paper/2512.09247/) (2025)
- [PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment](https://mlsanity.com/paper/2505.11468/) (2025)
- [LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers](https://mlsanity.com/paper/2505.23758/) (2025)
- [LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering](https://mlsanity.com/paper/2508.07647/) (2025)
- [Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers](https://mlsanity.com/paper/2603.05769/) (2026)
- [MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues](https://mlsanity.com/paper/2512.03046/) (2025)
- [VideoMaMa: Mask-Guided Video Matting via Generative Prior](https://mlsanity.com/paper/2601.14255/) (2026)
- [Multi-Agent Amodal Completion: Direct Synthesis with Fine-Grained Semantic Guidance](https://mlsanity.com/paper/2509.17757/) (2025)
- [UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors](https://mlsanity.com/paper/2605.00658/) (2026)
- [TAUE: Training-free Noise Transplant and Cultivation Diffusion Model](https://mlsanity.com/paper/2511.02580/) (2025)
- [LiWi: Layering in the Wild](https://mlsanity.com/paper/2605.14552/) (2026)
- [Does Synthetic Layered Design Data Benefit Layered Design Decomposition?](https://mlsanity.com/paper/2605.15167/) (2026)
- [Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning](https://mlsanity.com/paper/2605.30257/) (2026)
- [Text-Conditioned Background Generation for Editable Multi-Layer Documents](https://mlsanity.com/paper/2512.17151/) (2025)
- [A Unified and Controllable Framework for Layered Image Generation with Visual Effects](https://mlsanity.com/paper/2601.15507/) (2026)
- [Trajectory-Guided Diffusion for Foreground-Preserving Background Generation in Multi-Layer Documents](https://mlsanity.com/paper/2601.21857/) (2026)
- [LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency](https://mlsanity.com/paper/2605.10319/) (2026)
- [BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer](https://mlsanity.com/paper/2605.24894/) (2026)
- [Vera: A Layered Diffusion Model for Content-Preserving Video Editing](https://mlsanity.com/paper/2606.23610/) (2026)

## Abstract (arXiv)

Large-scale diffusion models have achieved remarkable success in generating high-quality images from textual descriptions, gaining popularity across various applications. However, the generation of layered content, such as transparent images with foreground and background layers, remains an under-explored area. Layered content generation is crucial for creative workflows in fields like graphic design, animation, and digital art, where layer-based approaches are fundamental for flexible editing and composition. In this paper, we propose a novel image generation pipeline based on Latent Diffusion Models (LDMs) that generates images with two layers: a foreground layer (RGBA) with transparency information and a background layer (RGB). Unlike existing methods that generate these layers sequentially, our approach introduces a harmonized generation mechanism that enables dynamic interactions between the layers for more coherent outputs. We demonstrate the effectiveness of our method through extensive qualitative and quantitative experiments, showing significant improvements in visual coherence, image quality, and layer consistency compared to baseline methods.