CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models
This addresses the challenge of identity-consistent character generation for applications in media and entertainment, though it is incremental as it builds on existing GAN and diffusion model techniques.
The paper tackles the problem of generating images with consistent new character identities using text-to-image models, proposing CharacterFactory, a framework that trains a GAN to map latent space to celebrity embeddings and achieves identity consistency in various contexts with only 10 minutes of training.
Recent advances in text-to-image models have opened new frontiers in human-centric generation. However, these models cannot be directly employed to generate images with consistent newly coined identities. In this work, we propose CharacterFactory, a framework that allows sampling new characters with consistent identities in the latent space of GANs for diffusion models. More specifically, we consider the word embeddings of celeb names as ground truths for the identity-consistent generation task and train a GAN model to learn the mapping from a latent space to the celeb embedding space. In addition, we design a context-consistent loss to ensure that the generated identity embeddings can produce identity-consistent images in various contexts. Remarkably, the whole model only takes 10 minutes for training, and can sample infinite characters end-to-end during inference. Extensive experiments demonstrate excellent performance of the proposed CharacterFactory on character creation in terms of identity consistency and editability. Furthermore, the generated characters can be seamlessly combined with the off-the-shelf image/video/3D diffusion models. We believe that the proposed CharacterFactory is an important step for identity-consistent character generation. Project page is available at: https://qinghew.github.io/CharacterFactory/.