ControlVAR: Exploring Controllable Visual Autoregressive Modeling
This work addresses the problem of efficient and flexible conditional image generation for AI researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackles the challenges of high computational cost and inference latency in conditional visual generation by introducing ControlVAR, a framework for controllable visual autoregressive modeling that achieves superior performance compared to popular conditional diffusion models like ControlNet and T2I-Adaptor across various tasks.
Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, high inference latency, and difficulties of integration with large language models (LLMs) have necessitated exploring alternatives to DMs. This paper introduces ControlVAR, a novel framework that explores pixel-level controls in visual autoregressive (VAR) modeling for flexible and efficient conditional generation. In contrast to traditional conditional models that learn the conditional distribution, ControlVAR jointly models the distribution of image and pixel-level conditions during training and imposes conditional controls during testing. To enhance the joint modeling, we adopt the next-scale AR prediction paradigm and unify control and image representations. A teacher-forcing guidance strategy is proposed to further facilitate controllable generation with joint modeling. Extensive experiments demonstrate the superior efficacy and flexibility of ControlVAR across various conditional generation tasks against popular conditional DMs, \eg, ControlNet and T2I-Adaptor. Code: \url{https://github.com/lxa9867/ControlVAR}.