Z_image's "if you know, you know" NSFW LoRA model. It is recommended to save the latent and decode it locally. On the cloud, they will all be red-tagged images. For VAE decoding, download the VAE model here: https://modelscope.cn/models/Comfy-Org/z_image_turbo/resolve/master/split_files/vae/ae.safetensors