KNN-Diffusion: Image Generation via Large-Scale Retrieval

Figure 1: (a) Samples of stickers generated from text inputs, (b) Semantic text-guided manipulations applied to the "Original" image without using edit masks. In both cases, our model was trained without any text data. Recent text-to-image models have achieved impressive results. However, since they require large-scale datasets of text-image pairs, it is impractical to train them on new domains where data is scarce or not labeled. In this work, we propose using large-scale retrieval methods, in particular, efficient k-Nearest-Neighbors (kNN), which offers novel capabilities: (1) training a substantially small and efficient text-to-image diffusion model without any text, (2) generating out-ofdistribution images by simply swapping the retrieval database at inference time, and (3) performing text-driven local semantic manipulations while preserving object identity. To demonstrate the robustness of our method, we apply our kNN approach on two state-of-the-art diffusion backbones, and show results on several different datasets. As evaluated by human studies and automatic metrics, our method achieves state-of-the-art results compared to existing approaches that train text-to-image generation models using images only (without paired text data). Large-scale generative models have been applied successfully to image generation tasks (Gafni et al., 2022; Ramesh et al., 2021; Nichol et al., 2021; Saharia et al., 2022; Yu et al., 2022), and have shown outstanding capabilities in extending human creativity using editing and user control. However, these models face several significant challenges: (i) Large-scale paired data requirement. To achieve high-quality results, text-to-image models rely heavily on large-scale datasets of (text, image) pairs collected from the internet. Due to the requirement of paired data, these models cannot be applied to new or customized domains with only unannotated images. Training these models on highly complex distributions of natural images usually requires scaling the size of the model, data, batch-size, and training time, which makes them challenging to train and less accessible to the community.