PrismGPT: Proxy-Guided Learning for Region-Aware Photo Editing with Self-Synthesized Reasoning
Pr PrismGPT, a Vision-Language Model (VLM) framework that produces structured, region-aware editing plans from a single input image without relying on commercial black-box tools is presented.
Ke Zhao, Hue Nguyen, Abhijith Punnappurath et al.
· 0 citations