2024/06/03 by Elad Richardson, Richardson, Elad, Yuval Alaluf +7 · 1 voice · 1 citation
Computer Science · #Advanced Mathematical Modeling in Engineering #cs.CV
paper · pdf · doi:10.48550/arxiv.2406.01300
openalex publication_date 2024/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Text-guided image generation enables the creation of visual content from textual descriptions. However, certain visual concepts cannot be effectively conveyed through language alone. This has sparked a renewed interest in utilizing the CLIP image embedding space for more visually-oriented tasks through methods such as IP-Adapter. Interestingly, the CLIP image embedding space has been shown to be semantically meaningful, where linear operations within this space yield semantically meaningful results. Yet, the specific meaning of these operations can vary unpredictably across different images. To harness this potential, we introduce pOps, a framework that trains specific semantic operators directly on CLIP image embeddings. Each pOps operator is built upon a pretrained Diffusion Prior model. While the Diffusion Prior model was originally trained to map between text embeddings and image embeddings, we demonstrate that it can be tuned to accommodate new input conditions, resulting in a diffusion operator. Working directly over image embeddings not only improves our ability to learn semantic operations but also allows us to directly use a textual CLIP loss as an additional supervision when needed. We show that pOps can be used to learn a variety of photo-inspired operators with distinct semantic meanings, highlighting the semantic diversity and potential of our proposed approach.