fix random seeding of latent

[matpalm]

for whatever reason tf.random.normal doesn't honour the passed seed...

e.g. consider the following...

>>> import numpy as np
>>> import tensorflow as tf
>>> np.sum(tf.random.normal((1,2,3,4), seed=123))
2.359888
>>> np.sum(tf.random.normal((1,2,3,4), seed=123))
-0.19422567

this means the current latents generated aren't seeded. switching to numpy, which is fine here since the initial latents aren't in the TF graph at all, fixes things.

[matpalm]

apprently this is the expected behaviour of tf.random.normal !!!

https://twitter.com/fchollet/status/1572725572937322497

[divamgupta]

Thanks for the PR. Could you replace the other tf.random.normal call as well?

[matpalm]

the noise one? that's actually not being used ( see https://github.com/divamgupta/stable-diffusion-tensorflow/issues/21 ) i'd recommend removing it completely...

[matpalm]

oh. oops. pushed that matmul change to the wrong branch. muddies this PR but it's a thing to do anyways to be honest

[matpalm]

superseded by https://github.com/divamgupta/stable-diffusion-tensorflow/pull/32