许可证：Apache-2.0
数据集：

• google/docci
• google/imageinwords
• ProGamerGov/synthetic-dataset-1m-dalle3-high-quality-captions
  语言：
• 英文
  库名称：transformers
  管道标签：图像文本到文本
  标签：
• 艺术

pip install -q datasets flash_attn timm einops

from transformers import AutoModelForCausalLM, AutoProcessor, AutoConfig
import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model = AutoModelForCausalLM.from_pretrained("gokaygokay/Florence-2-SD3-Captioner", trust_remote_code=True).to(device).eval()
processor = AutoProcessor.from_pretrained("gokaygokay/Florence-2-SD3-Captioner", trust_remote_code=True)

# 运行模型的示例函数
def run_example(task_prompt, text_input, image):
    prompt = task_prompt + text_input

    # 确保图像为RGB模式
    if image.mode != "RGB":
        image = image.convert("RGB")

    inputs = processor(text=prompt, images=image, return_tensors="pt").to(device)
    generated_ids = model.generate(
        input_ids=inputs["input_ids"],
        pixel_values=inputs["pixel_values"],
        max_new_tokens=1024,
        num_beams=3
    )
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
    parsed_answer = processor.post_process_generation(generated_text, task=task_prompt, image_size=(image.width, image.height))
    return parsed_answer

from PIL import Image
import requests
import copy

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)
answer = run_example("<DESCRIPTION>", "详细描述这张图片。", image)
final_answer = answer['<DESCRIPTION>']
print(final_answer)

# '在一个阳光明媚的日子里，从平视角度拍摄，一辆浅蓝色的大众甲壳虫停在鹅卵石街道上。甲壳虫停在一栋黄色建筑前，建筑有两扇棕色的门。画面右侧的门是白色的，而左侧的门是深蓝色的。车头正对镜头，停在街道中央。'