Imagic: Text-Based Real Image Editing with Diffusion Models

🤖 Plain-English Summary

Text-conditioned image editing has recently attracted considerable interest. To better assess performance, we introduce TEdBench, a highly challenging image editing benchmark.

🔑 Key Findings

• However, most methods are currently limited to one of the following: specific editing types (e.g., object overlay, style transfer), synthetically generated images, or requiring multiple input images of a common object.
• In this paper we demonstrate, for the very first time, the ability to apply complex (e.g., non-rigid) text-based semantic edits to a single real image.
• For example, we can change the posture and composition of one or multiple objects inside an image, while preserving its original characteristics.

🔗 Related Resources