🌈 CustomNet: Zero-Shot Object Customization with
Variable-Viewpoints in Text-to-Image Diffusion Models

Ziyang Yuan1,2, Mingdeng Cao2,3, Xintao Wang2✉, Zhongang Qi2, Chun Yuan1✉ Ying Shan2,
1Tsinghua University, 2ARC Lab, Tencent PCG, 3The University of Tokyo

We proposed CustomNet, a zero-shot customization method that can generate harmonious customized images with explicit Viewpoints, Location, and Background(text/image) controls simultaneously, while ensuring identity preservation.

Real world Objects Control


Incorporating a customized object into image generation presents an attractive feature in text-to-image generation. However, existing optimization-based and encoder-based methods are hindered by drawbacks such as time-consuming optimization, insufficient identity preservation, and a prevalent copy-pasting effect. To overcome these limitations, we introduce CustomNet, a novel object customization approach that explicitly incorporates 3D novel view synthesis capabilities into the object customization process. This integration facilitates the adjustment of spatial position relationships and viewpoints, yielding diverse outputs while effectively preserving object identity. Moreover, we introduce delicate designs to enable location control and flexible background control through textual descriptions or specific user-defined images, overcoming the limitations of existing 3D novel view synthesis methods. We further leverage a dataset construction pipeline that can better handle real-world objects and complex backgrounds. Equipped with these designs, our method facilitates zero-shot object customization without test-time optimization, offering simultaneous control over the location, viewpoints, and background. As a result, our CustomNet ensures enhanced identity preservation and generates diverse, harmonious outputs.


To achieve the customization genertation, we propose the model training and inference pipeline and dataset construction pipeline

Model Pipeline

Overview of our proposed CustomNet. CustomNet is able to simultaneously control viewpoint, location, and background in a unified framework, thereby achieving harmonious customized image generation while effectively preserving object identity and texture details. The background generation can be controlled either through textual descriptions (the ‘Generation’ branch) or by providing a specific user-defined image (the ‘Composition’ branch).

Data Construction Pipeline

Data construction pipeline from 3D objects (a) and single image (b).

Comparison Results

Qualitative comparison. Our CustomNet demonstrates superior capacities in terms of identity preservation, viewpoint control, and harmony of the customized image.


                title={CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models}, 
                author={Ziyang Yuan and Mingdeng Cao and Xintao Wang and Zhongang Qi and Chun Yuan and Ying Shan},