camp2 lmdeploy llava运行时输入高分辨率图片会返回空字符串

camp2 lmdeploy llava运行时输入高分辨率图片会返回空字符串

项目地址 https://github.com/InternLM/Tutorial/blob/camp2/lmdeploy/README.md#61-%E4%BD%BF%E7%94%A8lmdeploy%E8%BF%90%E8%A1%8C%E8%A7%86%E8%A7%89%E5%A4%9A%E6%A8%A1%E6%80%81%E5%A4%A7%E6%A8%A1%E5%9E%8Bllava

当输入一张分辨率为 1920*1080 分辨率的图片时不会返回文字
打印response时显示text为空

解决方法为手动降低分辨率
```python
import gradio as gr
from lmdeploy import pipeline

# pipe = pipeline('liuhaotian/llava-v1.6-vicuna-7b') 非开发机运行此命令
pipe = pipeline('/share/new_models/liuhaotian/llava-v1.6-vicuna-7b')

def model(image, text):
if image is None:
return [(text, "请上传一张图片。")]
else:
width, height = image.size
print(f"width = {width}, height = {height}")

# 调整图片最长宽/高为256
if max(width, height) > 256:
ratio = max(width, height) / 256
n_width = int(width / ratio)
n_height = int(height / ratio)
print(f"new width = {n_width}, new height = {n_height}")
image = image.resize((n_width, n_height))

response = pipe((text, image)).text
print(f"response: {response}")
return [(text, response)]

demo = gr.Interface(fn=model, inputs=[gr.Image(type="pil"), gr.Textbox()], outputs=gr.Chatbot())
demo.launch()
```

更改后效果可以正常返回text

Start with camp2/lmdeploy/README.md section 6.1 and reproduce the LLaVA example using a 1920×1080 image. Compare the empty response with the provided image-resizing workaround, then update the example or its handling so high-resolution inputs return text; verify the documented example produces a non-empty response.

Do mô hình lập chỉ mục viết ra từ nội dung của issue.