Negative prompts

[Juvuzux]

As implemented, is it currently possible to use negative prompts?

[sweetpalma]

I could second this question. Is there any way to use negative prompts?

[jorgemcgomes]

The negative prompt is simply the prompt that is used for the "unconditional" generation in Classifier-Free Guidance. In this implementation it is hardcoded to be an empty string (or rather, a sequence full of padding tokens, https://github.com/divamgupta/stable-diffusion-tensorflow/blob/master/stable_diffusion_tf/constants.py), which is how it was originally meant to be by the model developers.

It doesn't seem to be that hard to change the implementation to support any arbitrary prompt to be used for the unconditional guidance.

[divamgupta]

If anyone could send a PR with a Coab example, that would be great.