让不同AI画图模型互相接力，一张图能混着画
不同公司训练出的AI画图模型，内部结构互不兼容，就像说不同语言。但研究者发现一个反直觉的事实：这些模型虽然架构各异，对画面的空间理解却惊人地相似——把一张图从中间状态从一个模型交给另一个模型，粗看内容居然还能保住。基于这个发现，他们做了一个叫InstantFusion的轻量接口：给每个模型配一个翻译器，把各自的中间状态投影到一个共享空间，再解码成目标模型能读的格式。训练时用同一张图在相同噪声水平下的状态对齐，并同步局部去噪速度。训练好后，你可以在任意两个模型之间无缝切换去噪过程，不用为每对模型单独做映射。它能让生成加速、把多个模型的偏好组合起来、跨架构蒸馏，还能做跨模型合成。这不是你明天能直接用的工具，但它指向一个趋势：AI画图不再是一个模型单打独斗，而是可以像乐队一样，不同模型各展所长、接力完成一张图。
📄 原文摘要(英文)
Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations. Despite their remarkable generation capabilities, the cross-model alignment of latent representations and the consistency of their underlying denoising dynamics remain underexplored. In this work, we uncover an intriguing cross-model compatibility: independently trained generators exhibit similar latent spatial organization, while directly handing off intermediate states between unaligned models can still preserve coarse visual content. Motivated by these observations, we propose InstantFusion, a lightweight shared latent interface that connects the denoising trajectories of heterogeneous image generators. Specifically, to enable flexible cross-model state translation, model-specific Latent AutoEncoders (LAEs) are introduced to project intermediate states from different generators into a shared latent space and decode them into the latent space of a target generator. This shared space is constrained by two complementary objectives: aligning intermediate states derived from the same image at matched noise levels and synchronizing their corresponding local denoising velocities. Once trained, InstantFusion allows denoising to seamlessly transition across frozen generators without requiring a dedicated mapping for every model pair. The versatility of InstantFusion is demonstrated across acceleration, multi-preference composition, cross-architecture on-policy distillation, and cross-model composition, achieving competitive performance across these diverse settings.