EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models
By: Mingzhe Li , Gehao Zhang , Zhenting Wang and more
Potential Business Impact:
Finds the words that made a picture.
Text-to-image generation models~(e.g., Stable Diffusion) have achieved significant advancements, enabling the creation of high-quality and realistic images based on textual descriptions. Prompt inversion, the task of identifying the textual prompt used to generate a specific artifact, holds significant potential for applications including data attribution, model provenance, and watermarking validation. Recent studies introduced a delayed projection scheme to optimize for prompts representative of the vocabulary space, though challenges in semantic fluency and efficiency remain. Advanced image captioning models or visual large language models can generate highly interpretable prompts, but they often lack in image similarity. In this paper, we propose a prompt inversion technique called \sys for text-to-image diffusion models, which includes initializing embeddings using a pre-trained image captioning model, refining them through reverse-engineering in the latent space, and converting them to texts using an embedding-to-text model. Our experiments on the widely-used datasets, such as MS COCO, LAION, and Flickr, show that our method outperforms existing methods in terms of image similarity, textual alignment, prompt interpretability and generalizability. We further illustrate the application of our generated prompts in tasks such as cross-concept image synthesis, concept manipulation, evolutionary multi-concept generation and unsupervised segmentation.
Similar Papers
Textualize Visual Prompt for Image Editing via Diffusion Bridge
CV and Pattern Recognition
Makes editing photos easier with just one example.
Towards Evaluating Robustness of Prompt Adherence in Text to Image Models
CV and Pattern Recognition
Makes AI draw pictures that match words better.
Improving Text-to-Image Generation with Input-Side Inference-Time Scaling
Computation and Language
Makes computer pictures better from simple words.