We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Using negative prompts, I stumble unto a paradox: if you try to use a negative prompt to avoid NSFW like for example:
text_prompts: [ { text: "illustration", weight: 1.0 }, { text: "naked nude", weight: -1.0 }
the prompts are rejected by the API!
I tested and this is indeed the same behavior that in the studio, but… it doesn’t make sense!
Rejected prompts should be accepted as negative, shouldn’t they? That would help avoiding the filtered/blurred results, for example.
The text was updated successfully, but these errors were encountered:
This is a known issue downstream and we're currently working on a fix to resolve it. I agree it is a strange paradox.
Sorry, something went wrong.
No branches or pull requests
Using negative prompts, I stumble unto a paradox: if you try to use a negative prompt to avoid NSFW like for example:
text_prompts: [ { text: "illustration", weight: 1.0 }, { text: "naked nude", weight: -1.0 }
the prompts are rejected by the API!
I tested and this is indeed the same behavior that in the studio, but… it doesn’t make sense!
Rejected prompts should be accepted as negative, shouldn’t they? That would help avoiding the filtered/blurred results, for example.
The text was updated successfully, but these errors were encountered: