Latent Textual Space: Pivot for Scaling Customized Text-to-Image and Video Generation.
TL;DR
This paper introduces a novel Latent Textual Space (LTS), which is positioned after the text encoder and a linear projection layer, and develops LATEXBLEND-I/G/V inference pipelines for three prominent customized generation tasks, enabling seamless plug-and-play combination of multiple concepts.
Abstract
Customized generation synthesizes user-specified visual concepts into novel contexts conditioned on prompts. Scaling the number of concepts in customized generation meets a broader demand for personalization, whereas existing methods face challenges with generation quality and computational efficiency. In this paper, we introduce a novel Latent Textual Space (LTS), which is positioned after the text encoder and a linear projection layer. We identify that LTS is the pivot in text-conditional diffusion models, offering three key merits for scaling customized generation: 1) sufficient customized information, 2) effective mitigation of denoising deviation, and 3) excellent scalability. We devise a customization framework to embed each individual concept into compact features in LTS, serving as a versatile concept representation for customized generation. Based on the introduced LTS, we develop LATEXBLEND-I/G/V inference pipelines for three prominent customized generation tasks, enabling seamless plug-and-play combination of multiple concepts in customized text-to-image (T2I), grounded T2I, and inflation-based text-to-video (T2V) generation. These pipelines are built upon the core idea of Blending multiple single-concept representations in the Latent Textual Space, with dedicated designs to address the unique challenges specific to each task. Extensive experiments demonstrate that our method effectively addresses key challenges in scaling multi-concept customized generation, outperforming baselines in both generation quality and computational efficiency.