from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
from PIL import Image

pretrained = "snzhang/FilmTitle-Beit-GPT2"
model = VisionEncoderDecoderModel.from_pretrained(pretrained)
feature_extractor = ViTFeatureExtractor.from_pretrained(pretrained)
tokenizer = AutoTokenizer.from_pretrained(pretrained)

image_path = "your image path"
image = Image.open(image_path)
if image.mode != "RGB":
        image = image.convert("RGB")
pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values

output_ids = model.generate(pixel_values, **gen_kwargs)
preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
preds = [pred.strip() for pred in preds]
print(preds)

More Details

You can get more training details in FilmTitle-Beit-GPT2