Sijie Zhu

Multi-Reward as Condition for Instruction-based Image Editing

2024 · arXiv (Cornell University)

High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable Diffusion, DALL-E) which are not trained for image …