Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models
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
TL;DR
Edify Image introduces a novel pixel-space Laplacian diffusion approach for high-quality, photorealistic image generation across diverse applications like text-to-image synthesis and 4K upsampling.
Contribution
It presents a new cascaded diffusion model framework utilizing Laplacian diffusion for improved image fidelity and versatility.
Findings
Achieves photorealistic images with pixel-perfect accuracy
Supports diverse applications including HDR panoramas and image finetuning
Demonstrates superior quality over existing diffusion models
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Retrieval and Classification Techniques · Medical Image Segmentation Techniques · Image Processing Techniques and Applications
MethodsDiffusion