精進圖像：使用像素空間拉普拉斯擴散模型生成高質量圖像

Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models

November 11, 2024

作者: NVIDIA, Yuval Atzmon, Maciej Bala, Yogesh Balaji, Tiffany Cai, Yin Cui, Jiaojiao Fan, Yunhao Ge, Siddharth Gururani, Jacob Huffman, Ronald Isaac, Pooya Jannaty, Tero Karras, Grace Lam, J. P. Lewis, Aaron Licata, Yen-Chen Lin, Ming-Yu Liu, Qianli Ma, Arun Mallya, Ashlee Martino-Tarr, Doug Mendez, Seungjun Nah, Chris Pruett, Fitsum Reda, Jiaming Song, Ting-Chun Wang, Fangyin Wei, Xiaohui Zeng, Yu Zeng, Qinsheng Zhang

cs.AI

摘要

我們介紹 Edify Image，這是一系列能夠以像素級準確度生成逼真圖像內容的擴散模型。Edify Image 使用級聯像素空間擴散模型，透過一種新穎的拉普拉斯擴散過程進行訓練，該過程會以不同頻率帶的圖像信號以不同速率衰減。Edify Image 支援廣泛的應用，包括文本轉圖像合成、4K 超分辨率、ControlNets、360 HDR 全景生成，以及圖像定製的微調。

English

We introduce Edify Image, a family of diffusion models capable of generating photorealistic image content with pixel-perfect accuracy. Edify Image utilizes cascaded pixel-space diffusion models trained using a novel Laplacian diffusion process, in which image signals at different frequency bands are attenuated at varying rates. Edify Image supports a wide range of applications, including text-to-image synthesis, 4K upsampling, ControlNets, 360 HDR panorama generation, and finetuning for image customization.