I'm using replicate as the AI backend. They're the ones that are flagging the content. There's probably some tuning that I can do but I haven't dug into it.
You'll have to retry, rephrase, or edit the image to get past that.
The NSFW filter is in the stable-diffusion library you're calling. Disable the line that sets image, has_nsfw_concept in image2image.py, (or whatever your code calling the library looks like).
Yeah, that's what I meant, but inexplicitly was downvoted…
Correction: Replicate is handling this just fine. This setting is baked into Stable Diffusion.