IMAGE TO VIDEO
from transformers import AutoProcessor proc = AutoProcessor.from_pretrained(path, trust_remote_code=True) msgs = [{"role": "user", "content": [{"type": "image", "image": "photo.jpg"}, {"type": "text", "text": "描述这张图。"}]}] inputs = proc.apply_chat_template(msgs, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device) out = model.generate(**inputs, max_new_tokens=256) print(proc.batch_decode(out[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)[0])