CVJul 20

MixDiffusion: Mixing Diffusion-based Uni-condition Text-to-Image Generation Models for Multi-condition Image Synthesis

arXiv:2607.1763410.7
Predicted impact top 30% in CV · last 90 daysOriginality Incremental advance
AI Analysis

It provides a flexible, training-free framework for combining multiple control conditions in image generation, addressing a key limitation of existing single-condition methods.

MixDiffusion enables multi-condition text-to-image generation by integrating multiple pre-trained uni-condition diffusion models without additional training, supporting conditions like bounding boxes, keypoints, sketches, depth maps, reference images, and text.

Recent advances in text-to-image (T2I) generation have enabled controllable image synthesis by incorporating conditions beyond text. However, most existing diffusion-based methods are limited to a single type of control condition (e.g., bounding boxes or keypoints), which restricts their flexibility. To address this limitation, we propose MixDiffusion, a training-free diffusion framework for multi-condition T2I generation. MixDiffusion theoretically supports an arbitrary number of control conditions, including bounding boxes, keypoints, sketches, depth maps, reference images, and text, by collaboratively integrating multiple pre-trained uni-condition diffusion models. The key insight of the proposed approach is to derive the predicted noise distribution in each denoising step of the diffusion-based multi-condition image generation model from the predicted noise distributions of multiple diffusion-based uni-condition models with a derived integration formula, which is supported by rigorous theory proof. Owing to its training-free nature, MixDiffusion is easy to deploy and readily extensible to new control modalities.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes