These are LoRA adaption weights for stable-diffusion-v1-5/stable-diffusion-v1-5.
The weights were fine-tuned for forgetting ../PEM_composition_img_gen/assets/imagenette_splits/n03888257/train_forget dataset, while retaining ../PEM_composition_img_gen/assets/imagenette_splits/n03888257/train_retain.
You can find some example images in the following.