AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation

Yanan Sun, Yanchen Liu, Yinhao Tang, Wenjie Pei and Kai Chen*

Shanghai AI Laboratory

Overview

The field of text-to-image (T2I) generation has made significant progress in recent years, largely driven by advancements in diffusion models. Linguistic control enables effective content creation, but struggles with fine-grained control over image generation. This challenge has been explored, to a great extent, by incorporating additional usersupplied spatial conditions, such as depth maps and edge maps, into pre-trained T2I models through extra encoding. However, multi-control image synthesis still faces several challenges. Specifically, current approaches are limited in handling free combinations of diverse input control signals, overlook the complex relationships among multiple spatial conditions, and often fail to maintain semantic alignment with provided textual prompts. This can lead to suboptimal user experiences. To address these challenges, we propose AnyControl, a multi-control image synthesis framework that supports arbitrary combinations of diverse control signals. AnyControl develops a novel Multi-Control Encoder that extracts a unified multi-modal embedding to guide the generation process. This approach enables a holistic understanding of user inputs, and produces high-quality, faithful results under versatile control signals, as demonstrated by extensive quantitative and qualitative evaluations.

Model Card

AnyControl for SD 1.5

ckpts/anycontrol_15.ckpt: weights for AnyControl.
ckpts/init_local.ckpt: initial weights of AnyControl during training, generated following Uni-ControlNet.
ckpts/blip2_pretrained.pth: third-party model.
annotator/ckpts: third-party models used in annotators.

License and Citation

All models and assets are under the Apache 2.0 license unless specified otherwise.

If this work is helpful for your research, please consider citing the following BibTeX entry.

@misc{sun2024anycontrol,
  title={AnyControl: Create your artwork with versatile control on text-to-image generation},
  author={Sun, Yanan and Liu, Yanchen and Tang, Yinhao and Pei, Wenjie and Chen, Kai},
  booktitle={ECCV},
  year={2024}

}