Kvikontent

/

midjourney-v7

like 10

I tried creating an Image using the lora model, and I got this output saying that the prompt contains NSFW prompt. The output contains the prompt too.

     Creating the Image
     Enter a Prompt:
        Black Mercedes-Benz SUV 2026 model driving fast across a desert at sunset, raising a trail of dust, dramatic golden lighting, dynamic angle, luxury vehicle in rugged landscape, cinematic, high detail, sharp focus.
      100%                                         50/50 [00:25<00:00,  1.95it/s]
      Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed.
      Successfully the image in 26.424558401107788 seconds

      ![download](https://cdn-uploads.huggingface.co/production/uploads/66c6f070d1af9f7943e3907e/0ZRN_KPeYazYZiI6nwhxG.png)"

Another output:

     Creating the Image
     Enter a Prompt:
                 A majestic, radiant white unicorn with a glowing pearlescent horn and shimmering mane, standing in a dark, enchanted forest. The unicorn emits a    soft ethereal light that illuminates the gloomy, misty surroundings. Giant twisted trees, thick fog, bioluminescent mushrooms.Hyperrealistic image. High contrast between the luminous unicorn and the deep shadows of the forest, cinematic, fantasy art, dramatic lighting, 8k, hyper-detailed
     The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['cinematic , fantasy art , dramatic lighting , 8 k , hyper - detailed']
     100%                                           50/50 [00:26<00:00,  1.90it/s]
     Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed.
     Successfully the image in 27.07098150253296 seconds"

So I want to ask how can a Mercedes Benz and a Unicorn can be NSFW?