[DDIMInverseScheduler] `inf` values at first iteration when `set_alpha_to_one=True` and `prediction_type="sample"`

### Describe the bug

I got `inf` values in https://github.com/huggingface/diffusers/blob/560fb5f4d65b8593c13e4be50a59b1fd9c2d9992/src/diffusers/schedulers/scheduling_ddim_inverse.py#L347

because `beta_prod_t` is 0.0 at the first iteration, when `timestep` is < 0 and `beta_prod_t` is 0.0 (because `alpha_prod_t` is set to 1.0 when `set_alpha_to_one=True`).

https://github.com/huggingface/diffusers/blob/560fb5f4d65b8593c13e4be50a59b1fd9c2d9992/src/diffusers/schedulers/scheduling_ddim_inverse.py#L338

### Reproduction

```python
import torch as th
from diffusers import DDIMInverseScheduler

ddim_inverse_scheduler = DDIMInverseScheduler(
num_train_timesteps=1000,
prediction_type="sample",
set_alpha_to_one=True
)
ddim_inverse_scheduler.set_timesteps(num_inference_steps=50)

with th.no_grad():
pred = th.randn((1, 1, 2, 2, 2))
samples = th.randn((1, 1, 2, 2, 2))
t = 0
samples = ddim_inverse_scheduler.step(pred, t, samples).prev_sample
assert not th.isinf(samples).any(), "samples contain inf values"
```

### Logs

```shell

```

### System Info

- 🤗 Diffusers version: 0.32.2
- Platform: macOS-15.2-arm64-arm-64bit
- Running on Google Colab?: No
- Python version: 3.10.8
- PyTorch version (GPU?): 2.5.1 (False)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Huggingface_hub version: 0.29.1
- Transformers version: not installed
- Accelerate version: not installed
- PEFT version: not installed
- Bitsandbytes version: not installed
- Safetensors version: 0.5.2
- xFormers version: not installed
- Accelerator: Apple M1 Pro
- Using GPU in script?: No (Using MPS)
- Using distributed or parallel set-up in script?: No

### Who can help?

@yiyixuxu @sayakpaul

Inizia in src/diffusers/schedulers/scheduling_ddim_inverse.py, intorno alle righe 338 e 347, dove vengono calcolati i prodotti alpha e beta durante il primo passaggio. Esegui la riproduzione fornita di DDIMInverseScheduler con prediction_type="sample" e set_alpha_to_one=True, quindi verifica che il primo passaggio non produca valori inf.

Scritto dal modello di indicizzazione a partire dal testo della issue.