This project implements a neural network model to automatically colorize grayscale SAR images, transforming them into realistic RGB representations. The model uses a generator-discriminator ...
Stack: Stable Diffusion 1.5 + ControlNet (lineart) + IP-Adapter (color transfer) Requirements: NVIDIA GPU with 8GB+ VRAM (tested on RTX 4060), Python 3.11+ ./colorize -p ./chapter_01/ -r ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results