創造，而非複製！用於創意生成的推進能量擴散

ProCreate, Dont Reproduce! Propulsive Energy Diffusion for Creative Generation

August 5, 2024

作者: Jack Lu, Ryan Teehan, Mengye Ren

cs.AI

摘要

本文提出了ProCreate，這是一種簡單且易於實現的方法，用於提高基於擴散的圖像生成模型的樣本多樣性和創造力，並防止訓練數據的復制。ProCreate作用於一組參考圖像，並在生成過程中積極推動生成的圖像嵌入遠離參考嵌入。我們提出了FSCG-8（Few-Shot Creative Generation 8），這是一個包含不同概念、風格和設置的八個不同類別的少樣本創造性生成數據集，在其中ProCreate實現了最高的樣本多樣性和保真度。此外，我們展示了ProCreate在使用訓練文本提示進行大規模評估時有效防止複製訓練數據。代碼和FSCG-8可在https://github.com/Agentic-Learning-AI-Lab/procreate-diffusion-public找到。項目頁面位於https://procreate-diffusion.github.io。

English

In this paper, we propose ProCreate, a simple and easy-to-implement method to improve sample diversity and creativity of diffusion-based image generative models and to prevent training data reproduction. ProCreate operates on a set of reference images and actively propels the generated image embedding away from the reference embeddings during the generation process. We propose FSCG-8 (Few-Shot Creative Generation 8), a few-shot creative generation dataset on eight different categories -- encompassing different concepts, styles, and settings -- in which ProCreate achieves the highest sample diversity and fidelity. Furthermore, we show that ProCreate is effective at preventing replicating training data in a large-scale evaluation using training text prompts. Code and FSCG-8 are available at https://github.com/Agentic-Learning-AI-Lab/procreate-diffusion-public. The project page is available at https://procreate-diffusion.github.io.