[Bug]: Sampling error with V-Prediction model

[yamatazen]

What happened?

Sampling didn't work with V-Prediction model.

What did you expect would happen?

Successful image generation.

Relevant log output

Traceback (most recent call last):                                                              | 0/70 [00:00<?, ?it/s]
  File "C:\Users\yamat\Desktop\OneTrainer\modules\trainer\GenericTrainer.py", line 254, in __sample_loop:01,  1.05s/it]
    self.model_sampler.sample(
  File "C:\Users\yamat\Desktop\OneTrainer\modules\modelSampler\StableDiffusionXLSampler.py", line 471, in sample
    image = self.__sample_base(
  File "C:\Users\yamat\Desktop\OneTrainer\venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "C:\Users\yamat\Desktop\OneTrainer\modules\modelSampler\StableDiffusionXLSampler.py", line 171, in __sample_base
    latent_image = noise_scheduler.step(
  File "C:\Users\yamat\Desktop\OneTrainer\venv\src\diffusers\src\diffusers\schedulers\scheduling_euler_discrete.py", line 668, in step
    dt = self.sigmas[self.step_index + 1] - sigma_hat
IndexError: index 21 is out of bounds for dimension 0 with size 21
Error during sampling, proceeding without sampling

Output of pip freeze

No response

[O-J1]

What happened?

Sampling didn't work with V-Prediction model.

What did you expect would happen?

Successful image generation.

Relevant log output

Traceback (most recent call last):                                                              | 0/70 [00:00<?, ?it/s]
  File "C:\Users\yamat\Desktop\OneTrainer\modules\trainer\GenericTrainer.py", line 254, in __sample_loop:01,  1.05s/it]
    self.model_sampler.sample(
  File "C:\Users\yamat\Desktop\OneTrainer\modules\modelSampler\StableDiffusionXLSampler.py", line 471, in sample
    image = self.__sample_base(
  File "C:\Users\yamat\Desktop\OneTrainer\venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "C:\Users\yamat\Desktop\OneTrainer\modules\modelSampler\StableDiffusionXLSampler.py", line 171, in __sample_base
    latent_image = noise_scheduler.step(
  File "C:\Users\yamat\Desktop\OneTrainer\venv\src\diffusers\src\diffusers\schedulers\scheduling_euler_discrete.py", line 668, in step
    dt = self.sigmas[self.step_index + 1] - sigma_hat
IndexError: index 21 is out of bounds for dimension 0 with size 21
Error during sampling, proceeding without sampling

Output of pip freeze

No response

Please include your config.json export and your pip freeze.

[Nerogar]

Looks like the same issue as #468