Method inference

visual_chatgpt.py:291–298

(self, text)

                         "like: generate an image of an object or something, or generate an image that includes some objects. "
                         "The input to this tool should be a string, representing the text used to generate image. ")
    def inference(self, text):
        image_filename = os.path.join('image', f"{str(uuid.uuid4())[:8]}.png")
        prompt = text + ', ' + self.a_prompt
        image = self.pipe(prompt, negative_prompt=self.n_prompt).images[0]
        image.save(image_filename)
        print(
            f"\nProcessed Text2Image, Input Text: {text}, Output Image: {image_filename}")
        return image_filename


class ImageCaptioning: