Diba-Vision · دیبا-ویژن

from transformers import AutoModelForImageTextToText, AutoProcessor
import torch

model = AutoModelForImageTextToText.from_pretrained(
    "Dibachain/Diba-Vision", trust_remote_code=True, dtype=torch.bfloat16, device_map="auto")
processor = AutoProcessor.from_pretrained("Dibachain/Diba-Vision", trust_remote_code=True)

messages = [{"role": "user", "content": [
    {"type": "image", "image": "path/or/url/to/image.jpg"},
    {"type": "text", "text": "این تصویر را به فارسی توضیح بده."},
]}]

inputs = processor.apply_chat_template(messages, add_generation_prompt=True,
    tokenize=True, return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(processor.batch_decode(out[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)[0])