HunyuanVIdeo in diffusers use negative_prompt but generate wrong video

### Describe the bug

Diffusers support negative_prompt for hunyuan_video recently, but when I use negative_prompt and set **guidance_scale** and **true_cfg_scale**, I got a video with all black elements. Maybe I set wrong parameters or save video fail.
How can I fix my problem? Thanks

### Reproduction

import torch
import time
from diffusers import HunyuanVideoPipeline, HunyuanVideoTransformer3DModel, AutoencoderKLHunyuanVideo
from diffusers.utils import export_to_video, load_image, load_video
NEGATIVE_PROMPT = "Aerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion"
model_path = "/realpath/hunyuanvideo-community-HunyuanVideo"
pipe = HunyuanVideoPipeline.from_pretrained(model_path, torch_dtype=torch.float16)
pipe.vae.enable_tiling()
pipe.to("cuda")
output = pipe(
prompt="The video shows a man and a woman standing in the snow, wearing winter clothing and holding cups of coffee. ",
negative_prompt=NEGATIVE_PROMPT,
height=480,
width=720,
num_frames=129,
num_inference_steps=10,
true_cfg_scale=6.0,
guidance_scale=1.0,
).frames[0]
export_to_video(output, "diffusers_480p_output.mp4", fps=24)

### Logs

```shell

```

### System Info

H20
resolution = 480 * 720
steps=10

### Who can help?

_No response_

Start with the HunyuanVideoPipeline call in the reproduction, focusing on the interaction between negative_prompt, guidance_scale, and true_cfg_scale. Check whether the black output appears in the returned frames before export_to_video, then consult the pipeline's guidance and video-export behavior. Done means identifying whether the parameters or export step causes the black elements and documenting or fixing the reproducible case.

Escrito por el modelo de indexación a partir del texto del issue.