Trained kontext dev lora with 200 pairs (concatenated agnostic mask & cloth AND concatenated image-cloth target) with captions : "Replace the gray masked area with {caption}. Keep the person's face and pose details intact". For 2000 steps
You should use `` to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
