Conditional Text-to-Image Generation with Reference Guidance
This work addresses a specific challenge in text-to-image generation for users needing accurate visual text rendering, representing an incremental improvement with novel plugins.
The paper tackles the problem of text-to-image diffusion models struggling to precisely render subjects like text spelling by introducing reference-guided conditional generation, achieving superior results on tasks such as English and multi-lingual scene-text generation with plugins containing only 28.55M trainable parameters.
Text-to-image diffusion models have demonstrated tremendous success in synthesizing visually stunning images given textual instructions. Despite remarkable progress in creating high-fidelity visuals, text-to-image models can still struggle with precisely rendering subjects, such as text spelling. To address this challenge, this paper explores using additional conditions of an image that provides visual guidance of the particular subjects for diffusion models to generate. In addition, this reference condition empowers the model to be conditioned in ways that the vocabularies of the text tokenizer cannot adequately represent, and further extends the model's generalization to novel capabilities such as generating non-English text spellings. We develop several small-scale expert plugins that efficiently endow a Stable Diffusion model with the capability to take different references. Each plugin is trained with auxiliary networks and loss functions customized for applications such as English scene-text generation, multi-lingual scene-text generation, and logo-image generation. Our expert plugins demonstrate superior results than the existing methods on all tasks, each containing only 28.55M trainable parameters.