Method __call__

gen_img_diffusers.py:726–1300

r""" Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`): The prompt or prompts to guide the image generation. negative_prompt (`str` or `List[str]`, *optional*): The prompt or prompts

(
        self,
        prompt: Union[str, List[str]],
        negative_prompt: Optional[Union[str, List[str]]] = None,
        init_image: Union[torch.FloatTensor, PIL.Image.Image, List[PIL.Image.Image]] = None,
        mask_image: Union[torch.FloatTensor, PIL.Image.Image, List[PIL.Image.Image]] = None,
        height: int = 512,
        width: int = 512,
        num_inference_steps: int = 50,
        guidance_scale: float = 7.5,
        negative_scale: float = None,
        strength: float = 0.8,
        # num_images_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[torch.Generator] = None,
        latents: Optional[torch.FloatTensor] = None,
        max_embeddings_multiples: Optional[int] = 3,
        output_type: Optional[str] = "pil",
        vae_batch_size: float = None,
        return_latents: bool = False,
        # return_dict: bool = True,
        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
        is_cancelled_callback: Optional[Callable[[], bool]] = None,
        callback_steps: Optional[int] = 1,
        img2img_noise=None,
        clip_prompts=None,
        clip_guide_images=None,
        networks: Optional[List[LoRANetwork]] = None,
        **kwargs,
    )

    @torch.no_grad()
    def __call__(
        self,
        prompt: Union[str, List[str]],
        negative_prompt: Optional[Union[str, List[str]]] = None,
        init_image: Union[torch.FloatTensor, PIL.Image.Image, List[PIL.Image.Image]] = None,
        mask_image: Union[torch.FloatTensor, PIL.Image.Image, List[PIL.Image.Image]] = None,
        height: int = 512,
        width: int = 512,
        num_inference_steps: int = 50,
        guidance_scale: float = 7.5,
        negative_scale: float = None,
        strength: float = 0.8,
        # num_images_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[torch.Generator] = None,
        latents: Optional[torch.FloatTensor] = None,
        max_embeddings_multiples: Optional[int] = 3,
        output_type: Optional[str] = "pil",
        vae_batch_size: float = None,
        return_latents: bool = False,
        # return_dict: bool = True,
        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
        is_cancelled_callback: Optional[Callable[[], bool]] = None,
        callback_steps: Optional[int] = 1,
        img2img_noise=None,
        clip_prompts=None,
        clip_guide_images=None,
        networks: Optional[List[LoRANetwork]] = None,
        **kwargs,
    ):
        r"""
        Function invoked when calling the pipeline for generation.
        Args:
            prompt (`str` or `List[str]`):
                The prompt or prompts to guide the image generation.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
                if `guidance_scale` is less than `1`).
            init_image (`torch.FloatTensor` or `PIL.Image.Image`):
                `Image`, or tensor representing an image batch, that will be used as the starting point for the
                process.
            mask_image (`torch.FloatTensor` or `PIL.Image.Image`):
                `Image`, or tensor representing an image batch, to mask `init_image`. White pixels in the mask will be
                replaced by noise and therefore repainted, while black pixels will be preserved. If `mask_image` is a
                PIL image, it will be converted to a single channel (luminance) before use. If it's a tensor, it should
                contain one color channel (L) instead of 3, so the expected shape would be `(B, H, W, 1)`.
            height (`int`, *optional*, defaults to 512):
                The height in pixels of the generated image.
            width (`int`, *optional*, defaults to 512):
                The width in pixels of the generated image.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            guidance_scale (`float`, *optional*, defaults to 7.5):
                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,