跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-09AI 評分39

InstantFusion:異質圖像生成器的共享潛在介面

InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators

AI 導讀

InstantFusion 是連接異質圖像生成器去噪軌跡的輕量級共享潛在介面。它透過各模型專屬的 Latent AutoEncoders(LAEs),把中間狀態映射至共享潛在空間,再解碼至目標生成器的潛在空間。訓練後,去噪可在凍結生成器之間轉換,無須為每組模型配對另設映射,並在加速、多偏好組合等設定中取得具競爭力的表現。

正文

Published on Oct 9

Authors:

,

,

,

,

,

,

Abstract

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.

View arXiv page View PDF Project page GitHub 9 Add to collection

Get this paper in your agent:

hf papers read 2610.13944

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.13944 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.13944 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.13944 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co