Class CannyText2Image

visual_chatgpt.py:345–379

class CannyText2Image:
    def __init__(self, device):
        print(f"Initializing CannyText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-canny",
                                                          torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=StableDiffusionSafetyChecker.from_pretrained('CompVis/stable-diffusion-safety-checker'),
            torch_dtype=self.torch_dtype)
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                            'fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Canny Image",
             description="useful when you want to generate a new real image from both the user description and a canny image."
                         " like: generate a real image of a object or something from this canny image,"
                         " or generate a new real image of a object or something from this edge image. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description. ")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="canny2image")
        image.save(updated_image_path)
        print(f"\nProcessed CannyText2Image, Input Canny: {image_path}, Input Text: {instruct_text}, "
              f"Output Text: {updated_image_path}")
        return updated_image_path


class Image2Line: