Control the starting seed?

I wanted to make a PR, but I couldn’t figure out where would be the best place to intervene in the cascade of initialization calls upto Siren itself.

Compared to the original notebook, which randomizes its initial seed on each run, the deep-daze approach currently always seems to start with a very noir seed:

and amazingly CLIP is quite happy to navigate inside it and keep generating in that style (even when I would prefer a cheery light generation instead). Here are two examples of the types of generation one ends up with:

Ideally one would like to specify some hex color as “dominant” for the seed and expose that as a command line option, but I could do that myself if I found out where to look. Could you ( @lucidrains ) point me to the right general area where one would set a custom init seed for Siren?

[lucidrains]

@dginev I don’t think the seed is the problem, but since you brought it up, i added the ability to specify it with --seed in the latest version

[afiaka87]

@dginev I think we can close this issue now. I’m still sort of just generally curious about why the original research notebook gives a different initial color on the same value of theta (30.0) than this repo. But I believe the issue here covers too wide a range of discussion.