How to use inference for multiple prompt?

[foreverpiano]

I try to use a list of prompts and the predict input is List[str]. But it reported TypeError(f"prompt must be a string, but got {type(prompt)}")

        # ========================================================================
        # Arguments: prompt, new_prompt, negative_prompt
        # ========================================================================
        if not isinstance(prompt, str):
            raise TypeError(f"`prompt` must be a string, but got {type(prompt)}")
        prompt = [prompt.strip()]

        # negative prompt
        if negative_prompt is None or negative_prompt == "":
            negative_prompt = self.default_negative_prompt
        if not isinstance(negative_prompt, str):
            raise TypeError(
                f"`negative_prompt` must be a string, but got {type(negative_prompt)}"
            )
        negative_prompt = [negative_prompt.strip()]

which is opposite to prompt (str or List[str]): The input text.

        """
        Predict the image/video from the given text.

        Args:
            prompt (str or List[str]): The input text.
            kwargs:
                height (int): The height of the output video. Default is 192.
                width (int): The width of the output video. Default is 336.
                video_length (int): The frame number of the output video. Default is 129.
                seed (int or List[str]): The random seed for the generation. Default is a random integer.
                negative_prompt (str or List[str]): The negative text prompt. Default is an empty string.
                guidance_scale (float): The guidance scale for the generation. Default is 6.0.
                num_images_per_prompt (int): The number of images per prompt. Default is 1.
                infer_steps (int): The number of inference steps. Default is 100.
        """

[foreverpiano]

cc @JacobKong @TianQi-777 @xibosun

[JacobKong]

Thanks for your attention. We will fix this. You can try to run a single prompt first because more than one prompt will cause an oom error for high resolution using a single 80 G GPU.

[foreverpiano]

@JacobKong That's great. I suggest we sample from prompt.txt instead of the command line, as it would be easier to run benchmarks like VBench. I'm also curious about what huanyuan's VBench score is.

[gg22mm]

TypeError(f"`` must be a string, but got {type(prompt)}")

我尝试使用提示列表，预测输入是List[str]。但它报告了TypeError(f"提示 must be a string, but got {type(prompt)}")

        # ========================================================================
        # Arguments: prompt, new_prompt, negative_prompt
        # ========================================================================
        if not isinstance(prompt, str):
            raise TypeError(f"`prompt` must be a string, but got {type(prompt)}")
        prompt = [prompt.strip()]

        # negative prompt
        if negative_prompt is None or negative_prompt == "":
            negative_prompt = self.default_negative_prompt
        if not isinstance(negative_prompt, str):
            raise TypeError(
                f"`negative_prompt` must be a string, but got {type(negative_prompt)}"
            )
        negative_prompt = [negative_prompt.strip()]

prompt (str or List[str]): The input text.

这是相反的prompt (str or List[str]): The input text.

        """
        Predict the image/video from the given text.

        Args:
            prompt (str or List[str]): The input text.
            kwargs:
                height (int): The height of the output video. Default is 192.
                width (int): The width of the output video. Default is 336.
                video_length (int): The frame number of the output video. Default is 129.
                seed (int or List[str]): The random seed for the generation. Default is a random integer.
                negative_prompt (str or List[str]): The negative text prompt. Default is an empty string.
                guidance_scale (float): The guidance scale for the generation. Default is 6.0.
                num_images_per_prompt (int): The number of images per prompt. Default is 1.
                infer_steps (int): The number of inference steps. Default is 100.
        """

这个不就是四川熊猫那个吗？ ~~ #134