TokenCompose: Text-to-Image Diffusion with Token-level Supervision
This work addresses a specific bottleneck in text-to-image diffusion models for users needing precise multi-object composition, representing an incremental improvement.
The paper tackles the problem of inconsistent text-to-image generation in Latent Diffusion Models when composing multiple object categories, achieving significant improvements in multi-category instance composition and photorealism by finetuning Stable Diffusion with token-level supervision.
We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. Despite its tremendous success, the standard denoising process in the Latent Diffusion Model takes text prompts as conditions only, absent explicit constraint for the consistency between the text prompts and the image contents, leading to unsatisfactory results for composing multiple object categories. TokenCompose aims to improve multi-category instance composition by introducing the token-wise consistency terms between the image content and object segmentation maps in the finetuning stage. TokenCompose can be applied directly to the existing training pipeline of text-conditioned diffusion models without extra human labeling information. By finetuning Stable Diffusion, the model exhibits significant improvements in multi-category instance composition and enhanced photorealism for its generated images. Project link: https://mlpc-ucsd.github.io/TokenCompose