MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation

By Omer Bar-Tal, Lior Yariv, Yaron Lipman, Tali Dekel. International Conference on Machine Learning, 2023

624 citations recorded by the source corpus.

Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge, currently mostly addressed by costly and long re-training and fine-tuning or ad-hoc adaptations to specific image generation tasks. In this work, we present MultiDiffusion, a unified framework that enables versatile and controllable image generation, using a pre-trained text-to-image diffusion model, without any further training or finetuning. At the center of our approach is a new generation process, based on an optimization task that binds together multiple diffusion generation processes with a shared set of parameters or constraints. We show that MultiDiffusion can be readily applied to generate high quality and diverse images that adhere to user-provided controls, such as desired aspect ratio (e.g., panorama), and spatial guiding signals, ranging from tight segmentation masks to bounding boxes. Project webpage: https://multidiffusion.github.io

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9ced6e814457eae83f5415364e266143defc81d1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Training-Free Layout Control with Cross-Attention Guidance (2023, methodology): “For COCO 2014, we follow the same setup adopted by prior work [4], which uses only a subset of the annotated objects per image.”
TokenFlow: Consistent Diffusion Features for Consistent Video Editing (2023, background): “Much of this progress is also attributed to diffusion models [47, 8, 9, 14, 31] which have been established as state-of-the-art text-to-image generators [30, 41, 36, 38, 44, 2].”
LayoutGPT: Compositional Visual Planning and Generation with Large Language Models (2023, background): “While one could additionally integrate models that synthesize images with the guidance of layouts [56, 27, 2], keypoints [27], or sketches [21, 57], users still have to create fine-grained inputs on their own, resulting in extra efforts and degraded efficiency compared to using pure language instruc”
Adding Conditional Control to Text-to-Image Diffusion Models (2023, background): “Concurrent works [8, 9, 32, 56] examine a wide variety of ways to control diffusion models.”
OminiControl: Minimal and Universal Control for Diffusion Transformer (2024, neutral): “…approaches show clear task bias – they typically work well for either spatially aligned controls (e.g., edge-guided or depth-guided generation [2, 15, 29, 30, 37, 42, 52, 61, 63]) or spatially un-aligned ones (e.g., style transfer or subject-driven generation [18, 27, 28, 50, 60][14, 33]),…”
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image (2023, background): “MultiDiffusion [3] and SyncDif-fusion [35] correlate multiple diffusion models for different regions of a 2D image.”
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment (2024, background): “Some works [6, 11, 13, 20, 28, 31, 35, 44, 56] attempt to manipulate cross-attention maps or latents according to spatial or semantic constraints in the prompt.”