AttributeError when running demo code: 'str' object has no attribute 'size'

[GopiSumanth]

I'm trying to run the demo code from the Sa2VA-1B model repository. While executing the code, I encountered the following error:
Could you please help me resolve this issue?
Environment details:

Model: ByteDance/Sa2VA-1B
Source: Hugging Face Hub (https://huggingface.co/ByteDance/Sa2VA-1B)

code:

from transformers import AutoTokenizer, AutoModel
from PIL import Image
import numpy as np
import os

# load the model and tokenizer
path = "ByteDance/Sa2VA-1B"
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)


# for video chat
video_folder = "video"
images_paths = os.listdir(video_folder)
images_paths = [os.path.join(video_folder, image_name) for image_name in images_paths]
if len(images_paths) > 5:  # uniformly sample 5 frames
    step = (len(images_paths) - 1) // (5 - 1)
    images_paths = [images_paths[0]] + images_paths[1:-1][::step][1:] + [images_paths[-1]]
text_prompts = "<image>Please describe the video."
input_dict = {
    'video': images_paths,
    'text': text_prompts,
    'past_text': '',
    'mask_prompts': None,
    'tokenizer': tokenizer,
}
return_dict = model.predict_forward(**input_dict)
answer = return_dict["prediction"]

print("video response: ",answer)

Error:

Traceback (most recent call last):
  File "_codepath_", line 51, in <module>
    return_dict = model.predict_forward(**input_dict)
  File "_codepath_/.cache/huggingface/modules/transformers_modules/ByteDance/Sa2VA-1B/1059a41774e0541f4d2a333ae8e9b97b64901f89/modeling_sa2va_chat.py", line 601, in predict_forward
    ori_image_size = video[0].size
AttributeError: 'str' object has no attribute 'size'