Update pipeline.py

pipeline.py

@@ -459,14 +459,17 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
         self.enable_attention_slicing(None)
 
     @torch.no_grad()
-    def text2img(
+    def __call__(
             self,
             prompt: Union[str, List[str]],
+            negative_prompt: Optional[Union[str, List[str]]] = None,
+            init_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
+            mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
             height: int = 512,
             width: int = 512,
             num_inference_steps: int = 50,
             guidance_scale: float = 7.5,
-            negative_prompt: Optional[Union[str, List[str]]] = None,
+            strength: float = 0.8,
             num_images_per_prompt: Optional[int] = 1,
             eta: float = 0.0,
             generator: Optional[torch.Generator] = None,
@@ -484,6 +487,17 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
         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):
@@ -497,9 +511,12 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
                 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`,
                 usually at the expense of lower image quality.
-            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`).
+            strength (`float`, *optional*, defaults to 0.8):
+                Conceptually, indicates how much to transform the reference `init_image`. Must be between 0 and 1.
+                `init_image` will be used as a starting point, adding more noise to it the larger the `strength`. The
+                number of denoising steps depends on the amount of noise initially added. When `strength` is 1, added
+                noise will be maximum and the denoising process will run for the full number of iterations specified in
+                `num_inference_steps`. A value of 1, therefore, essentially ignores `init_image`.
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             eta (`float`, *optional*, defaults to 0.0):
@@ -542,6 +559,9 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
         else:
             raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
 
+        if strength < 0 or strength > 1:
+            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
+
         if height % 8 != 0 or width % 8 != 0:
             raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
 
@@ -586,35 +606,81 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             **kwargs
         )
 
-        # get the initial random noise unless the user supplied it
+        # set timesteps
+        self.scheduler.set_timesteps(num_inference_steps)
 
-        # Unlike in other pipelines, latents need to be generated in the target device
-        # for 1-to-1 results reproducibility with the CompVis implementation.
-        # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
-        if latents is None:
+        init_latents_orig = None
+        mask = None
+        noise = None
+
+        if init_image is None:
+            # get the initial random noise unless the user supplied it
+
+            # Unlike in other pipelines, latents need to be generated in the target device
+            # for 1-to-1 results reproducibility with the CompVis implementation.
+            # However this currently doesn't work in `mps`.
+            latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+
+            if latents is None:
+                if self.device.type == "mps":
+                    # randn does not exist on mps
+                    latents = torch.randn(latents_shape, generator=generator, device="cpu", dtype=latents_dtype).to(
+                        self.device
+                    )
+                else:
+                    latents = torch.randn(latents_shape, generator=generator, device=self.device, dtype=latents_dtype)
+            else:
+                if latents.shape != latents_shape:
+                    raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {latents_shape}")
+                latents = latents.to(self.device)
+
+            timesteps = self.scheduler.timesteps.to(self.device)
+
+            # scale the initial noise by the standard deviation required by the scheduler
+            latents = latents * self.scheduler.init_noise_sigma
+        else:
+            if isinstance(init_image, PIL.Image.Image):
+                init_image = preprocess_image(init_image)
+            # encode the init image into latents and scale the latents
+            init_image = init_image.to(device=self.device, dtype=latents_dtype)
+            init_latent_dist = self.vae.encode(init_image).latent_dist
+            init_latents = init_latent_dist.sample(generator=generator)
+            init_latents = 0.18215 * init_latents
+            init_latents = torch.cat([init_latents] * num_images_per_prompt, dim=0)
+            init_latents_orig = init_latents
+
+            # preprocess mask
+            if mask_image is not None:
+                if isinstance(mask_image, PIL.Image.Image):
+                    mask_image = preprocess_mask(mask_image)
+                mask_image = mask_image.to(device=self.device, dtype=latents_dtype)
+                mask = torch.cat([mask_image] * batch_size * num_images_per_prompt)
+
+                # check sizes
+                if not mask.shape == init_latents.shape:
+                    raise ValueError("The mask and init_image should be the same size!")
+
+            # get the original timestep using init_timestep
+            offset = self.scheduler.config.get("steps_offset", 0)
+            init_timestep = int(num_inference_steps * strength) + offset
+            init_timestep = min(init_timestep, num_inference_steps)
+
+            timesteps = self.scheduler.timesteps[-init_timestep]
+            timesteps = torch.tensor([timesteps] * batch_size * num_images_per_prompt, device=self.device)
+
+            # add noise to latents using the timesteps
             if self.device.type == "mps":
                 # randn does not exist on mps
-                latents = torch.randn(latents_shape, generator=generator, device="cpu", dtype=latents_dtype).to(
+                noise = torch.randn(init_latents.shape, generator=generator, device="cpu", dtype=latents_dtype).to(
                     self.device
                 )
             else:
-                latents = torch.randn(latents_shape, generator=generator, device=self.device, dtype=latents_dtype)
-        else:
-            if latents.shape != latents_shape:
-                raise ValueError(f"Unexpected latents shape, got {latents.shape}, expected {latents_shape}")
-            latents = latents.to(self.device)
-
-        # set timesteps
-        self.scheduler.set_timesteps(num_inference_steps)
-
-        # Some schedulers like PNDM have timesteps as arrays
-        # It's more optimized to move all timesteps to correct device beforehand
-        timesteps_tensor = self.scheduler.timesteps.to(self.device)
+                noise = torch.randn(init_latents.shape, generator=generator, device=self.device, dtype=latents_dtype)
+            latents = self.scheduler.add_noise(init_latents, noise, timesteps)
 
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
+            t_start = max(num_inference_steps - init_timestep + offset, 0)
+            timesteps = self.scheduler.timesteps[t_start:].to(self.device)
 
         # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
         # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
@@ -625,7 +691,7 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
         if accepts_eta:
             extra_step_kwargs["eta"] = eta
 
-        for i, t in enumerate(self.progress_bar(timesteps_tensor)):
+        for i, t in enumerate(self.progress_bar(timesteps)):
             # expand the latents if we are doing classifier free guidance
             latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
             latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
@@ -641,6 +707,11 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             # compute the previous noisy sample x_t -> x_t-1
             latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample
 
+            if mask is not None:
+                # masking
+                init_latents_proper = self.scheduler.add_noise(init_latents_orig, noise, torch.tensor([t]))
+                latents = (init_latents_proper * mask) + (latents * (1 - mask))
+
             # call the callback, if provided
             if callback is not None and i % callback_steps == 0:
                 callback(i, t, latents)
@@ -671,15 +742,106 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
 
         return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)
 
-    @torch.no_grad()
-    def img2img(
+    def text2img(
             self,
             prompt: Union[str, List[str]],
+            negative_prompt: Optional[Union[str, List[str]]] = None,
+            height: int = 512,
+            width: int = 512,
+            num_inference_steps: int = 50,
+            guidance_scale: float = 7.5,
+            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",
+            return_dict: bool = True,
+            callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
+            callback_steps: Optional[int] = 1,
+            **kwargs,
+    ):
+        r"""
+        Function for text-to-image 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`).
+            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`,
+                usually at the expense of lower image quality.
+            num_images_per_prompt (`int`, *optional*, defaults to 1):
+                The number of images to generate per prompt.
+            eta (`float`, *optional*, defaults to 0.0):
+                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
+                [`schedulers.DDIMScheduler`], will be ignored for others.
+            generator (`torch.Generator`, *optional*):
+                A [torch generator](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation
+                deterministic.
+            latents (`torch.FloatTensor`, *optional*):
+                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
+                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
+                tensor will ge generated by sampling using the supplied random `generator`.
+            max_embeddings_multiples (`int`, *optional*, defaults to `3`):
+                The max multiple length of prompt embeddings compared to the max output length of text encoder.
+            output_type (`str`, *optional*, defaults to `"pil"`):
+                The output format of the generate image. Choose between
+                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
+                plain tuple.
+            callback (`Callable`, *optional*):
+                A function that will be called every `callback_steps` steps during inference. The function will be
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+            callback_steps (`int`, *optional*, defaults to 1):
+                The frequency at which the `callback` function will be called. If not specified, the callback will be
+                called at every step.
+        Returns:
+            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
+            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
+            When returning a tuple, the first element is a list with the generated images, and the second element is a
+            list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
+            (nsfw) content, according to the `safety_checker`.
+        """
+        return self.__call__(
+            prompt=prompt,
+            negative_prompt=negative_prompt,
+            height=height,
+            width=width,
+            num_inference_steps=num_inference_steps,
+            guidance_scale=guidance_scale,
+            num_images_per_prompt=num_images_per_prompt,
+            eta=eta,
+            generator=generator,
+            latents=latents,
+            max_embeddings_multiples=max_embeddings_multiples,
+            output_type=output_type,
+            return_dict=return_dict,
+            callback=callback,
+            callback_steps=callback_steps,
+            **kwargs
+        )
+
+    def img2img(
+            self,
             init_image: Union[torch.FloatTensor, PIL.Image.Image],
+            prompt: Union[str, List[str]],
+            negative_prompt: Optional[Union[str, List[str]]] = None,
             strength: float = 0.8,
             num_inference_steps: Optional[int] = 50,
             guidance_scale: Optional[float] = 7.5,
-            negative_prompt: Optional[Union[str, List[str]]] = None,
             num_images_per_prompt: Optional[int] = 1,
             eta: Optional[float] = 0.0,
             generator: Optional[torch.Generator] = None,
@@ -691,14 +853,16 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             **kwargs,
     ):
         r"""
-        Function invoked when calling the pipeline for generation.
-
+        Function for image-to-image generation.
         Args:
-            prompt (`str` or `List[str]`):
-                The prompt or prompts to guide the image generation.
             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.
+            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`).
             strength (`float`, *optional*, defaults to 0.8):
                 Conceptually, indicates how much to transform the reference `init_image`. Must be between 0 and 1.
                 `init_image` will be used as a starting point, adding more noise to it the larger the `strength`. The
@@ -714,9 +878,6 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
                 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`,
                 usually at the expense of lower image quality.
-            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`).
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             eta (`float`, *optional*, defaults to 0.0):
@@ -739,7 +900,6 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.
-
         Returns:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
@@ -747,169 +907,33 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
             (nsfw) content, according to the `safety_checker`.
         """
-        if isinstance(prompt, str):
-            batch_size = 1
-        elif isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if strength < 0 or strength > 1:
-            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
-
-        if (callback_steps is None) or (
-                callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
-        ):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-
-        # set timesteps
-        self.scheduler.set_timesteps(num_inference_steps)
-
-        if isinstance(init_image, PIL.Image.Image):
-            init_image = preprocess_image(init_image)
-
-        # get prompt text embeddings
-
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-        # get unconditional embeddings for classifier free guidance
-        uncond_tokens = [""]
-        if do_classifier_free_guidance:
-            if type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError("The length of `negative_prompt` should be equal to batch_size.")
-            else:
-                uncond_tokens = negative_prompt
-
-        text_embeddings = get_weighted_text_embeddings(
-            pipe=self,
+        return self.__call__(
             prompt=prompt,
-            uncond_prompt=uncond_tokens if do_classifier_free_guidance else None,
+            negative_prompt=negative_prompt,
+            init_image=init_image,
+            num_inference_steps=num_inference_steps,
+            guidance_scale=guidance_scale,
+            strength=strength,
+            num_images_per_prompt=num_images_per_prompt,
+            eta=eta,
+            generator=generator,
             max_embeddings_multiples=max_embeddings_multiples,
+            output_type=output_type,
+            return_dict=return_dict,
+            callback=callback,
+            callback_steps=callback_steps,
             **kwargs
         )
 
-        # encode the init image into latents and scale the latents
-        latents_dtype = text_embeddings.dtype
-        init_image = init_image.to(device=self.device, dtype=latents_dtype)
-        init_latent_dist = self.vae.encode(init_image).latent_dist
-        init_latents = init_latent_dist.sample(generator=generator)
-        init_latents = 0.18215 * init_latents
-
-        if isinstance(prompt, str):
-            prompt = [prompt]
-        if len(prompt) > init_latents.shape[0] and len(prompt) % init_latents.shape[0] == 0:
-            # expand init_latents for batch_size
-            deprecation_message = (
-                f"You have passed {len(prompt)} text prompts (`prompt`), but only {init_latents.shape[0]} initial"
-                " images (`init_image`). Initial images are now duplicating to match the number of text prompts. Note"
-                " that this behavior is deprecated and will be removed in a version 1.0.0. Please make sure to update"
-                " your script to pass as many init images as text prompts to suppress this warning."
-            )
-            deprecate("len(prompt) != len(init_image)", "1.0.0", deprecation_message, standard_warn=False)
-            additional_image_per_prompt = len(prompt) // init_latents.shape[0]
-            init_latents = torch.cat([init_latents] * additional_image_per_prompt * num_images_per_prompt, dim=0)
-        elif len(prompt) > init_latents.shape[0] and len(prompt) % init_latents.shape[0] != 0:
-            raise ValueError(
-                f"Cannot duplicate `init_image` of batch size {init_latents.shape[0]} to {len(prompt)} text prompts."
-            )
-        else:
-            init_latents = torch.cat([init_latents] * num_images_per_prompt, dim=0)
-
-        # get the original timestep using init_timestep
-        offset = self.scheduler.config.get("steps_offset", 0)
-        init_timestep = int(num_inference_steps * strength) + offset
-        init_timestep = min(init_timestep, num_inference_steps)
-
-        timesteps = self.scheduler.timesteps[-init_timestep]
-        timesteps = torch.tensor([timesteps] * batch_size * num_images_per_prompt, device=self.device)
-
-        # add noise to latents using the timesteps
-        noise = torch.randn(init_latents.shape, generator=generator, device=self.device, dtype=latents_dtype)
-        init_latents = self.scheduler.add_noise(init_latents, noise, timesteps)
-
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        latents = init_latents
-
-        t_start = max(num_inference_steps - init_timestep + offset, 0)
-
-        # Some schedulers like PNDM have timesteps as arrays
-        # It's more optimized to move all timesteps to correct device beforehand
-        timesteps = self.scheduler.timesteps[t_start:].to(self.device)
-
-        for i, t in enumerate(self.progress_bar(timesteps)):
-            # expand the latents if we are doing classifier free guidance
-            latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
-            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-            # predict the noise residual
-            noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
-
-            # perform guidance
-            if do_classifier_free_guidance:
-                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-            # compute the previous noisy sample x_t -> x_t-1
-            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample
-
-            # call the callback, if provided
-            if callback is not None and i % callback_steps == 0:
-                callback(i, t, latents)
-
-        latents = 1 / 0.18215 * latents
-        image = self.vae.decode(latents).sample
-
-        image = (image / 2 + 0.5).clamp(0, 1)
-        image = image.cpu().permute(0, 2, 3, 1).numpy()
-
-        if self.safety_checker is not None:
-            safety_checker_input = self.feature_extractor(self.numpy_to_pil(image), return_tensors="pt").to(
-                self.device
-            )
-            image, has_nsfw_concept = self.safety_checker(
-                images=image, clip_input=safety_checker_input.pixel_values.to(text_embeddings.dtype)
-            )
-        else:
-            has_nsfw_concept = None
-
-        if output_type == "pil":
-            image = self.numpy_to_pil(image)
-
-        if not return_dict:
-            return (image, has_nsfw_concept)
-
-        return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)
-
-    @torch.no_grad()
     def inpaint(
             self,
-            prompt: Union[str, List[str]],
             init_image: Union[torch.FloatTensor, PIL.Image.Image],
             mask_image: Union[torch.FloatTensor, PIL.Image.Image],
+            prompt: Union[str, List[str]],
+            negative_prompt: Optional[Union[str, List[str]]] = None,
             strength: float = 0.8,
             num_inference_steps: Optional[int] = 50,
             guidance_scale: Optional[float] = 7.5,
-            negative_prompt: Optional[Union[str, List[str]]] = None,
             num_images_per_prompt: Optional[int] = 1,
             eta: Optional[float] = 0.0,
             generator: Optional[torch.Generator] = None,
@@ -921,11 +945,8 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             **kwargs,
     ):
         r"""
-        Function invoked when calling the pipeline for generation.
-
+        Function for inpaint.
         Args:
-            prompt (`str` or `List[str]`):
-                The prompt or prompts to guide the image generation.
             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. This is the image whose masked region will be inpainted.
@@ -934,6 +955,11 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
                 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)`.
+            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`).
             strength (`float`, *optional*, defaults to 0.8):
                 Conceptually, indicates how much to inpaint the masked area. Must be between 0 and 1. When `strength`
                 is 1, the denoising process will be run on the masked area for the full number of iterations specified
@@ -948,9 +974,6 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
                 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`,
                 usually at the expense of lower image quality.
-            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`).
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             eta (`float`, *optional*, defaults to 0.0):
@@ -973,7 +996,6 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.
-
         Returns:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
@@ -981,156 +1003,21 @@ class StableDiffusionLongPromptWeightingPipeline(DiffusionPipeline):
             list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
             (nsfw) content, according to the `safety_checker`.
         """
-        if isinstance(prompt, str):
-            batch_size = 1
-        elif isinstance(prompt, list):
-            batch_size = len(prompt)
-        else:
-            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
-
-        if strength < 0 or strength > 1:
-            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
-
-        if (callback_steps is None) or (
-                callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
-        ):
-            raise ValueError(
-                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
-                f" {type(callback_steps)}."
-            )
-
-        # set timesteps
-        self.scheduler.set_timesteps(num_inference_steps)
-
-        # get prompt text embeddings
-
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-        # get unconditional embeddings for classifier free guidance
-        uncond_tokens = [""]
-        if do_classifier_free_guidance:
-            if type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt]
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = negative_prompt
-
-        text_embeddings = get_weighted_text_embeddings(
-            pipe=self,
+        return self.__call__(
             prompt=prompt,
-            uncond_prompt=uncond_tokens if do_classifier_free_guidance else None,
+            negative_prompt=negative_prompt,
+            init_image=init_image,
+            mask_image=mask_image,
+            num_inference_steps=num_inference_steps,
+            guidance_scale=guidance_scale,
+            strength=strength,
+            num_images_per_prompt=num_images_per_prompt,
+            eta=eta,
+            generator=generator,
             max_embeddings_multiples=max_embeddings_multiples,
+            output_type=output_type,
+            return_dict=return_dict,
+            callback=callback,
+            callback_steps=callback_steps,
             **kwargs
         )
-
-        # preprocess image
-        if not isinstance(init_image, torch.FloatTensor):
-            init_image = preprocess_image(init_image)
-
-        # encode the init image into latents and scale the latents
-        latents_dtype = text_embeddings.dtype
-        init_image = init_image.to(device=self.device, dtype=latents_dtype)
-        init_latent_dist = self.vae.encode(init_image).latent_dist
-        init_latents = init_latent_dist.sample(generator=generator)
-        init_latents = 0.18215 * init_latents
-
-        # Expand init_latents for batch_size and num_images_per_prompt
-        init_latents = torch.cat([init_latents] * batch_size * num_images_per_prompt, dim=0)
-        init_latents_orig = init_latents
-
-        # preprocess mask
-        if not isinstance(mask_image, torch.FloatTensor):
-            mask_image = preprocess_mask(mask_image)
-        mask_image = mask_image.to(device=self.device, dtype=latents_dtype)
-        mask = torch.cat([mask_image] * batch_size * num_images_per_prompt)
-
-        # check sizes
-        if not mask.shape == init_latents.shape:
-            raise ValueError("The mask and init_image should be the same size!")
-
-        # get the original timestep using init_timestep
-        offset = self.scheduler.config.get("steps_offset", 0)
-        init_timestep = int(num_inference_steps * strength) + offset
-        init_timestep = min(init_timestep, num_inference_steps)
-
-        timesteps = self.scheduler.timesteps[-init_timestep]
-        timesteps = torch.tensor([timesteps] * batch_size * num_images_per_prompt, device=self.device)
-
-        # add noise to latents using the timesteps
-        noise = torch.randn(init_latents.shape, generator=generator, device=self.device, dtype=latents_dtype)
-        init_latents = self.scheduler.add_noise(init_latents, noise, timesteps)
-
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        latents = init_latents
-
-        t_start = max(num_inference_steps - init_timestep + offset, 0)
-
-        # Some schedulers like PNDM have timesteps as arrays
-        # It's more optimized to move all timesteps to correct device beforehand
-        timesteps = self.scheduler.timesteps[t_start:].to(self.device)
-
-        for i, t in enumerate(self.progress_bar(timesteps)):
-            # expand the latents if we are doing classifier free guidance
-            latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
-            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
-
-            # predict the noise residual
-            noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
-
-            # perform guidance
-            if do_classifier_free_guidance:
-                noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-            # compute the previous noisy sample x_t -> x_t-1
-            latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample
-            # masking
-            init_latents_proper = self.scheduler.add_noise(init_latents_orig, noise, torch.tensor([t]))
-
-            latents = (init_latents_proper * mask) + (latents * (1 - mask))
-
-            # call the callback, if provided
-            if callback is not None and i % callback_steps == 0:
-                callback(i, t, latents)
-
-        latents = 1 / 0.18215 * latents
-        image = self.vae.decode(latents).sample
-
-        image = (image / 2 + 0.5).clamp(0, 1)
-        image = image.cpu().permute(0, 2, 3, 1).numpy()
-
-        if self.safety_checker is not None:
-            safety_checker_input = self.feature_extractor(self.numpy_to_pil(image), return_tensors="pt").to(
-                self.device
-            )
-            image, has_nsfw_concept = self.safety_checker(images=image, clip_input=safety_checker_input.pixel_values)
-        else:
-            has_nsfw_concept = None
-
-        if output_type == "pil":
-            image = self.numpy_to_pil(image)
-
-        if not return_dict:
-            return (image, has_nsfw_concept)
-
-        return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)