Different generation with `Diffusers` in I2V tasks for LTX-video

### Describe the bug

Hello, I encountered an issue with the generation when attempting the I2V task using `Diffusers`. Is there any difference between the `diffusers` implementation and the `LTX-video-inference scripts` in the I2V task?

- The above is the result from the `inference.py`, and the following is the result generated with `diffuser`.
- Prompts: `a person`

https://github.com/user-attachments/assets/6e2aeeaf-c52b-402c-ae92-aff2d325464b

https://github.com/user-attachments/assets/59f815ad-1746-4ec5-ae1c-a47dcfa0fd02

https://github.com/user-attachments/assets/8ca3c79b-8003-4fa2-82b1-8ae17beccb9c

- test img

Besides, it seems that the text prompt has a significant impact on the I2V generation with 'diffusers'. Could I be missing any important arguments?
https://huggingface.co/docs/diffusers/api/pipelines/ltx_video
- results

https://github.com/user-attachments/assets/c062c21f-5611-4860-ba17-441dd26a8913

https://github.com/user-attachments/assets/991ec853-ee26-43a7-914b-622d115a9b7f

https://github.com/user-attachments/assets/ff3e7f04-c17d-4f0a-9aba-2db68aae792d

https://github.com/user-attachments/assets/f2699759-c36e-4839-bddd-37b84a85e2c7

### Reproduction

- for LTX-video generation
https://github.com/Lightricks/LTX-Video/blob/main/inference.py
```
python inference.py \
--ckpt_path ./pretrained_models/LTX-Video \
--output_path './samples' \
--prompt "A person." \
--input_image_path ./samples/test_cases.png \
--height 512 \
--width 512 \
--num_frames 49 \
--seed 42
```

- for diffuser generation: it seems that the negative prompts are causing the issues. However, even when I remove them, the results are still not satisfactory.
```
import argparse
import torch
from diffusers import LTXVideoTransformer3DModel
from diffusers import LTXImageToVideoPipeline
from diffusers import FlowMatchEulerDiscreteScheduler, AutoencoderKLLTXVideo
from diffusers.utils import export_to_video, load_image, load_video

from moviepy import VideoFileClip, AudioFileClip
import numpy as np
from pathlib import Path
import os
import imageio
from einops import rearrange
from PIL import Image
import random

def seed_everething(seed: int):
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed(seed)

def generate_video(args):

pipe = LTXImageToVideoPipeline.from_pretrained(args.ltx_model_path, torch_dtype=torch.bfloat16)
pipe.to("cuda")

negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

image = load_image(args.validation_image)
prompt = "A person."
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
generator = torch.Generator(
device="cuda" if torch.cuda.is_available() else "cpu"
).manual_seed(42)

video = pipe(
image=image,
prompt=prompt,
guidance_scale=3,
# stg_scale=1,
generator=generator,
callback_on_step_end=None,
negative_prompt=negative_prompt,
width=512,
height=512,
num_frames=49,
num_inference_steps=50,
decode_timestep=0.05,
decode_noise_scale=0.025,

).frames[0]
export_to_video(video, args.output_file, fps=24)
```

- for demo images with difference text prompts
https://huggingface.co/docs/diffusers/api/pipelines/ltx_video

```
import torch
from diffusers import LTXImageToVideoPipeline
from diffusers.utils import export_to_video, load_image

pipe = LTXImageToVideoPipeline.from_pretrained("./pretrained_models/LTX-Video", torch_dtype=torch.bfloat16)
pipe.to("cuda")

image = load_image("samples/image.png")
prompt = "A young girl stands."
negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

video = pipe(
image=image,
prompt=prompt,
negative_prompt=negative_prompt,
width=704,
height=480,
num_frames=161,
num_inference_steps=50,
).frames[0]
modified_prompt = "-".join(prompt.split()[:14])
export_to_video(video, f"samples/test_out/demo-{modified_prompt}.mp4", fps=24)
```

### Logs

```shell

```

### System Info

torch 2.4.1
torchao 0.7.0
torchvision 0.19.1
diffusers 0.32.1
python 3.10

### Who can help?

_No response_

Compare the LTX-Video inference.py entry point with the LTXImageToVideoPipeline call in the reproduction, using the listed torch, diffusers, and Python versions. Reproduce both outputs with the same image, prompt, dimensions, frame count, seed, and steps, then identify whether a documented argument or implementation difference explains the mismatch.

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