Thank you for your contribution, but I can't make sense of the three curves in Figure 3.

[Supzekun]

Curve 1: Figure III left (Signal-to-noise ratio (SNR) of linear and cosine noise schedules for reference.) The relationship is given in your paper:

However when I use linear schedule locally, Diffusion Steps = 1000, and SNR by Equation 4, the curve is like this:

---

Curve 2: Figure III right（Weights of P2 weighting and the baseline with a linear schedule.）The relationship is given in your paper:

However when I use linear schedule locally, Diffusion Steps = 1000, and SNR by Equation 4, weight by

and P2-weight by

set k = 1, γ =1.
Also, I understand that you used the normalization operation: so I scaled weight to a range of 0 to 1 by maximum and minimum values
However, the curve I get is this:

These curves do not match at all the results you gave in your paper, did I do any step wrong? I am very interested in this article and look forward to your reply, thanks!

[Supzekun]

Attached below is the code I used to reproduce these curves:

[cheald]

In your first graph, your y-axis is linear scale, while the SNR graph from the paper is log scale. Also note that the linear schedule has SNR as the x-axis, rather than timestep.

Using the DDPMScheduler scaled_linear betas formulation (ie, for Stable Diffusion), and using timestep for the lambda_prime series:

[Supzekun]

In your first graph, your y-axis is linear scale, while the SNR graph from the paper is log scale. Also note that the linear schedule has SNR as the x-axis, rather than timestep.

Using the DDPMScheduler scaled_linear betas formulation (ie, for Stable Diffusion), and using timestep for the lambda_prime series:

I understand why, thank you very much for your help.