# TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

arXiv: https://arxiv.org/abs/2410.05591 · HTML: https://mlsanity.com/paper/2410.05591/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 42 of its 45 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 42)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [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)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [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)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [Improving Diffusion Models for Inverse Problems using Manifold Constraints](https://mlsanity.com/paper/2206.00941/) (2022)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [Diffusion Models already have a Semantic Latent Space](https://mlsanity.com/paper/2210.10960/) (2022)
- [Pix2Video: Video Editing using Image Diffusion](https://mlsanity.com/paper/2303.12688/) (2023)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)

## Built on by (most cited first, 14 of 14)

- [Reangle-A-Video: 4D Video Generation as Video-to-Video Translation](https://mlsanity.com/paper/2503.09151/) (2025)
- [Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts](https://mlsanity.com/paper/2502.07802/) (2025)
- [Personalize Anything for Free with Diffusion Transformer](https://mlsanity.com/paper/2503.12590/) (2025)
- [Mod-Adapter: Tuning-Free and Versatile Multi-concept Personalization via Modulation Adapter](https://mlsanity.com/paper/2505.18612/) (2025)
- [JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation](https://mlsanity.com/paper/2503.23951/) (2025)
- [Steer Away From Mode Collisions: Improving Composition In Diffusion Models](https://mlsanity.com/paper/2509.25940/) (2025)
- [MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion](https://mlsanity.com/paper/2510.13702/) (2025)
- [Composing Concepts from Images and Videos via Concept-prompt Binding](https://mlsanity.com/paper/2512.09824/) (2025)
- [AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization](https://mlsanity.com/paper/2512.23537/) (2025)
- [Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds](https://mlsanity.com/paper/2608.03135/) (2026)
- [Style Composition within Distinct LoRA modules for Traditional Art](https://mlsanity.com/paper/2507.11986/) (2025)
- [TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward](https://mlsanity.com/paper/2607.21606/) (2026)
- [MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding](https://mlsanity.com/paper/2608.03708/) (2026)
- [Stabilizing Camera-Controlled Novel View Synthesis at Inference Time](https://mlsanity.com/paper/2609.03639/) (2026)

## Abstract (arXiv)

Despite significant advancements in customizing text-to-image and video generation models, generating images and videos that effectively integrate multiple personalized concepts remains a challenging task. To address this, we present TweedieMix, a novel method for composing customized diffusion models during the inference phase. By analyzing the properties of reverse diffusion sampling, our approach divides the sampling process into two stages. During the initial steps, we apply a multiple object-aware sampling technique to ensure the inclusion of the desired target objects. In the later steps, we blend the appearances of the custom concepts in the de-noised image space using Tweedie's formula. Our results demonstrate that TweedieMix can generate multiple personalized concepts with higher fidelity than existing methods. Moreover, our framework can be effortlessly extended to image-to-video diffusion models, enabling the generation of videos that feature multiple personalized concepts. Results and source code are in our anonymous project page.