# Modulating Pretrained Diffusion Models for Multimodal Image Synthesis

arXiv: https://arxiv.org/abs/2302.12764 · HTML: https://mlsanity.com/paper/2302.12764/

## Key facts

- Cited by 23 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 56 of its 64 references that are in the map.
- First posted on arXiv 24 Feb 2023.

## 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, 30 of 56)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)

## Built on by (most cited first, 23 of 23)

- [BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout](https://mlsanity.com/paper/2308.01661/) (2023)
- [Controllable Generation with Text-to-Image Diffusion Models: A Survey](https://mlsanity.com/paper/2403.04279/) (2024)
- [DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control](https://mlsanity.com/paper/2312.03048/) (2023)
- [FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models](https://mlsanity.com/paper/2312.03517/) (2023)
- [Fine-grained Controllable Video Generation via Object Appearance and Context](https://mlsanity.com/paper/2312.02919/) (2023)
- [ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance](https://mlsanity.com/paper/2405.17532/) (2024)
- [Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters](https://mlsanity.com/paper/2311.18763/) (2023)
- [Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation](https://mlsanity.com/paper/2306.00914/) (2023)
- [Masked-Attention Diffusion Guidance for Spatially Controlling Text-to-Image Generation](https://mlsanity.com/paper/2308.06027/) (2023)
- [Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation](https://mlsanity.com/paper/2401.17664/) (2024)
- [Vision + Language Applications: A Survey](https://mlsanity.com/paper/2305.14598/) (2023)
- [Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation](https://mlsanity.com/paper/2310.12583/) (2023)
- [PARASOL: Parametric Style Control for Diffusion Image Synthesis](https://mlsanity.com/paper/2303.06464/) (2023)
- [Diffusion Model Compression for Image-to-Image Translation](https://mlsanity.com/paper/2401.17547/) (2024)
- [Towards Flexible, Scalable, and Adaptive Multi-Modal Conditioned Face Synthesis](https://mlsanity.com/paper/2312.16274/) (2023)
- [Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images](https://mlsanity.com/paper/2410.21826/) (2024)
- [DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation](https://mlsanity.com/paper/2412.03255/) (2024)
- [MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising](https://mlsanity.com/paper/2312.10899/) (2023)
- [LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions](https://mlsanity.com/paper/2404.13579/) (2024)
- [Generative AI in Map-Making: A Technical Exploration and Its Implications for Cartographers](https://mlsanity.com/paper/2508.18959/) (2025)
- [SketchingReality: From Freehand Scene Sketches To Photorealistic Images](https://mlsanity.com/paper/2602.14648/) (2026)
- [Multiple Noises in Diffusion Model for Semi-Supervised Multi-Domain Translation](https://mlsanity.com/paper/2309.14394/) (2023)
- [Appearance Pointers -- Multimodal Region Control of Diffusion Transformers](https://mlsanity.com/paper/2607.19344/) (2026)

## Abstract (arXiv)

We present multimodal conditioning modules (MCM) for enabling conditional image synthesis using pretrained diffusion models. Previous multimodal synthesis works rely on training networks from scratch or fine-tuning pretrained networks, both of which are computationally expensive for large, state-of-the-art diffusion models. Our method uses pretrained networks but textitdoes not require any updates to the diffusion network's parameters. MCM is a small module trained to modulate the diffusion network's predictions during sampling using 2D modalities (e.g., semantic segmentation maps, sketches) that were unseen during the original training of the diffusion model. We show that MCM enables user control over the spatial layout of the image and leads to increased control over the image generation process. Training MCM is cheap as it does not require gradients from the original diffusion net, consists of only ~1% of the number of parameters of the base diffusion model, and is trained using only a limited number of training examples. We evaluate our method on unconditional and text-conditional models to demonstrate the improved control over the generated images and their alignment with respect to the conditioning inputs.