Add Timestep Sampling Function from SD3 Branch to SD

[gesen2egee]

This PR introduces the timestep_sampling feature from SD3 Branch into the original SD model. The new timestep sampling options offer a more concentrated probability distribution compared to the default uniform sampling, which helps the model focus on specific aspects of learning. The new options can be used via the --timestep_sampling argument.

• Default (uniform): Keeps the original uniform timestep sampling, which evenly distributes the learning steps.
• Sigmoid: Behaves similarly to shift by default --discrete_flow_shift = 1.
• Shift: Skews the timestep distribution, helping the model concentrate on style learning or specific objects.
• Flux Shift: This option shift with the image size, similar to how FLUX behaves in larger images

Additional Parameters:

• --discrete_flow_shift: By default set to 1, uses random normal distribution to sample timesteps. A rightward shift helps the model focus more on style, while a leftward shift aids in learning specific objects. The default value is 1, providing a balanced form.
• --sigmoid_scale: Adjusts the shape of the sigmoid function.
  

While flux_shift maintains the distortion effects of FLUX, its application may vary in SD due to differences in model nature and training at fixed resolutions.

It is recommended to use the --timestep_sampling sigmoid option, combined with --soft_min_snr_gamma = 1
By rockerBOO #1068
#1068
for better results, as these settings seem to significantly improve model performance.

Suggested to merge this PR along with the soft min snr gamma PR.

[kohya-ss]

It looks like this PR is trying to merge all the changes from the sd3 branch into main, please make any fixes within the sd3 branch.

[gesen2egee]

I got it, open #1671 and close this.