diffusers 0.26.3__py3-none-any.whl → 0.27.0__py3-none-any.whl

diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py

@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -54,7 +54,7 @@ from ...utils import (
     unscale_lora_layers,
 )
 from ...utils.torch_utils import is_compiled_module, randn_tensor
-from ..pipeline_utils import DiffusionPipeline
+from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from ..stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
 
 
@@ -157,7 +157,11 @@ def retrieve_latents(
 
 
 class StableDiffusionXLControlNetImg2ImgPipeline(
-    DiffusionPipeline, TextualInversionLoaderMixin, StableDiffusionXLLoraLoaderMixin, IPAdapterMixin
+    DiffusionPipeline,
+    StableDiffusionMixin,
+    TextualInversionLoaderMixin,
+    StableDiffusionXLLoraLoaderMixin,
+    IPAdapterMixin,
 ):
     r"""
     Pipeline for image-to-image generation using Stable Diffusion XL with ControlNet guidance.
@@ -271,39 +275,6 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
         self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
         self.register_to_config(requires_aesthetics_score=requires_aesthetics_score)
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_slicing
-    def enable_vae_slicing(self):
-        r"""
-        Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
-        compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
-        """
-        self.vae.enable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_slicing
-    def disable_vae_slicing(self):
-        r"""
-        Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_tiling
-    def enable_vae_tiling(self):
-        r"""
-        Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
-        compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
-        processing larger images.
-        """
-        self.vae.enable_tiling()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_tiling
-    def disable_vae_tiling(self):
-        r"""
-        Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_tiling()
-
     # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl.StableDiffusionXLPipeline.encode_prompt
     def encode_prompt(
         self,
@@ -400,7 +371,7 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
             prompt_2 = prompt_2 or prompt
             prompt_2 = [prompt_2] if isinstance(prompt_2, str) else prompt_2
 
-            # textual inversion: procecss multi-vector tokens if necessary
+            # textual inversion: process multi-vector tokens if necessary
             prompt_embeds_list = []
             prompts = [prompt, prompt_2]
             for prompt, tokenizer, text_encoder in zip(prompts, tokenizers, text_encoders):
@@ -565,31 +536,54 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
             return image_embeds, uncond_image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
-    def prepare_ip_adapter_image_embeds(self, ip_adapter_image, device, num_images_per_prompt):
-        if not isinstance(ip_adapter_image, list):
-            ip_adapter_image = [ip_adapter_image]
+    def prepare_ip_adapter_image_embeds(
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
+    ):
+        if ip_adapter_image_embeds is None:
+            if not isinstance(ip_adapter_image, list):
+                ip_adapter_image = [ip_adapter_image]
 
-        if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
-            raise ValueError(
-                f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-            )
+            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
+                raise ValueError(
+                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
+                )
 
-        image_embeds = []
-        for single_ip_adapter_image, image_proj_layer in zip(
-            ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
-        ):
-            output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-            single_image_embeds, single_negative_image_embeds = self.encode_image(
-                single_ip_adapter_image, device, 1, output_hidden_state
-            )
-            single_image_embeds = torch.stack([single_image_embeds] * num_images_per_prompt, dim=0)
-            single_negative_image_embeds = torch.stack([single_negative_image_embeds] * num_images_per_prompt, dim=0)
+            image_embeds = []
+            for single_ip_adapter_image, image_proj_layer in zip(
+                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
+            ):
+                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
+                single_image_embeds, single_negative_image_embeds = self.encode_image(
+                    single_ip_adapter_image, device, 1, output_hidden_state
+                )
+                single_image_embeds = torch.stack([single_image_embeds] * num_images_per_prompt, dim=0)
+                single_negative_image_embeds = torch.stack(
+                    [single_negative_image_embeds] * num_images_per_prompt, dim=0
+                )
 
-            if self.do_classifier_free_guidance:
-                single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
-                single_image_embeds = single_image_embeds.to(device)
+                if do_classifier_free_guidance:
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                    single_image_embeds = single_image_embeds.to(device)
 
-            image_embeds.append(single_image_embeds)
+                image_embeds.append(single_image_embeds)
+        else:
+            repeat_dims = [1]
+            image_embeds = []
+            for single_image_embeds in ip_adapter_image_embeds:
+                if do_classifier_free_guidance:
+                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
+                    single_image_embeds = single_image_embeds.repeat(
+                        num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:]))
+                    )
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(
+                        num_images_per_prompt, *(repeat_dims * len(single_negative_image_embeds.shape[1:]))
+                    )
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(
+                        num_images_per_prompt, *(repeat_dims * len(single_image_embeds.shape[1:]))
+                    )
+                image_embeds.append(single_image_embeds)
 
         return image_embeds
 
@@ -625,6 +619,8 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
         negative_prompt_embeds=None,
         pooled_prompt_embeds=None,
         negative_pooled_prompt_embeds=None,
+        ip_adapter_image=None,
+        ip_adapter_image_embeds=None,
         controlnet_conditioning_scale=1.0,
         control_guidance_start=0.0,
         control_guidance_end=1.0,
@@ -795,6 +791,21 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
             if end > 1.0:
                 raise ValueError(f"control guidance end: {end} can't be larger than 1.0.")
 
+        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
+            raise ValueError(
+                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
+            )
+
+        if ip_adapter_image_embeds is not None:
+            if not isinstance(ip_adapter_image_embeds, list):
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
+                )
+            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     # Copied from diffusers.pipelines.controlnet.pipeline_controlnet_sd_xl.StableDiffusionXLControlNetPipeline.check_image
     def check_image(self, image, prompt, prompt_embeds):
         image_is_pil = isinstance(image, PIL.Image.Image)
@@ -871,6 +882,8 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
 
         t_start = max(num_inference_steps - init_timestep, 0)
         timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
+        if hasattr(self.scheduler, "set_begin_index"):
+            self.scheduler.set_begin_index(t_start * self.scheduler.order)
 
         return timesteps, num_inference_steps - t_start
 
@@ -1015,34 +1028,6 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
             self.vae.decoder.conv_in.to(dtype)
             self.vae.decoder.mid_block.to(dtype)
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_freeu
-    def enable_freeu(self, s1: float, s2: float, b1: float, b2: float):
-        r"""Enables the FreeU mechanism as in https://arxiv.org/abs/2309.11497.
-
-        The suffixes after the scaling factors represent the stages where they are being applied.
-
-        Please refer to the [official repository](https://github.com/ChenyangSi/FreeU) for combinations of the values
-        that are known to work well for different pipelines such as Stable Diffusion v1, v2, and Stable Diffusion XL.
-
-        Args:
-            s1 (`float`):
-                Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to
-                mitigate "oversmoothing effect" in the enhanced denoising process.
-            s2 (`float`):
-                Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to
-                mitigate "oversmoothing effect" in the enhanced denoising process.
-            b1 (`float`): Scaling factor for stage 1 to amplify the contributions of backbone features.
-            b2 (`float`): Scaling factor for stage 2 to amplify the contributions of backbone features.
-        """
-        if not hasattr(self, "unet"):
-            raise ValueError("The pipeline must have `unet` for using FreeU.")
-        self.unet.enable_freeu(s1=s1, s2=s2, b1=b1, b2=b2)
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_freeu
-    def disable_freeu(self):
-        """Disables the FreeU mechanism if enabled."""
-        self.unet.disable_freeu()
-
     @property
     def guidance_scale(self):
         return self._guidance_scale
@@ -1090,6 +1075,7 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
         pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         ip_adapter_image: Optional[PipelineImageInput] = None,
+        ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
@@ -1140,15 +1126,15 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
                 The width in pixels of the generated image. Anything below 512 pixels won't work well for
                 [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
                 and checkpoints that are not specifically fine-tuned on low resolutions.
+            strength (`float`, *optional*, defaults to 0.8):
+                Indicates extent to transform the reference `image`. Must be between 0 and 1. `image` is used as a
+                starting point and more noise is added the higher the `strength`. The number of denoising steps depends
+                on the amount of noise initially added. When `strength` is 1, added noise is maximum and the denoising
+                process runs for the full number of iterations specified in `num_inference_steps`. A value of 1
+                essentially ignores `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.
-            strength (`float`, *optional*, defaults to 0.3):
-                Conceptually, indicates how much to transform the reference `image`. Must be between 0 and 1. `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`.
             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
@@ -1189,6 +1175,11 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
                 weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
                 input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
+            ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
+                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters.
+                Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should contain the negative image embedding
+                if `do_classifier_free_guidance` is set to `True`.
+                If not provided, embeddings are computed from the `ip_adapter_image` input argument.
             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`.
@@ -1312,6 +1303,8 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
             negative_prompt_embeds,
             pooled_prompt_embeds,
             negative_pooled_prompt_embeds,
+            ip_adapter_image,
+            ip_adapter_image_embeds,
             controlnet_conditioning_scale,
             control_guidance_start,
             control_guidance_end,
@@ -1368,9 +1361,13 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
         )
 
         # 3.2 Encode ip_adapter_image
-        if ip_adapter_image is not None:
+        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare image and controlnet_conditioning_image
@@ -1535,7 +1532,7 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
                     down_block_res_samples = [torch.cat([torch.zeros_like(d), d]) for d in down_block_res_samples]
                     mid_block_res_sample = torch.cat([torch.zeros_like(mid_block_res_sample), mid_block_res_sample])
 
-                if ip_adapter_image is not None:
+                if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
                     added_cond_kwargs["image_embeds"] = image_embeds
 
                 # predict the noise residual
@@ -1590,7 +1587,22 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
                 self.upcast_vae()
                 latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
 
-            image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
+            # unscale/denormalize the latents
+            # denormalize with the mean and std if available and not None
+            has_latents_mean = hasattr(self.vae.config, "latents_mean") and self.vae.config.latents_mean is not None
+            has_latents_std = hasattr(self.vae.config, "latents_std") and self.vae.config.latents_std is not None
+            if has_latents_mean and has_latents_std:
+                latents_mean = (
+                    torch.tensor(self.vae.config.latents_mean).view(1, 4, 1, 1).to(latents.device, latents.dtype)
+                )
+                latents_std = (
+                    torch.tensor(self.vae.config.latents_std).view(1, 4, 1, 1).to(latents.device, latents.dtype)
+                )
+                latents = latents * latents_std / self.vae.config.scaling_factor + latents_mean
+            else:
+                latents = latents / self.vae.config.scaling_factor
+
+            image = self.vae.decode(latents, return_dict=False)[0]
 
             # cast back to fp16 if needed
             if needs_upcasting:

diffusers/pipelines/controlnet/pipeline_flax_controlnet.py

@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -156,7 +156,7 @@ class FlaxStableDiffusionControlNetPipeline(FlaxDiffusionPipeline):
         self.dtype = dtype
 
         if safety_checker is None:
-            logger.warn(
+            logger.warning(
                 f"You have disabled the safety checker for {self.__class__} by passing `safety_checker=None`. Ensure"
                 " that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered"
                 " results in services or applications open to the public. Both the diffusers team and Hugging Face"

diffusers/pipelines/dance_diffusion/pipeline_dance_diffusion.py

@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diffusers/pipelines/ddim/pipeline_ddim.py

@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diffusers/pipelines/ddpm/pipeline_ddpm.py

@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diffusers/pipelines/deepfloyd_if/pipeline_if.py

@@ -416,13 +416,13 @@ class IFPipeline(DiffusionPipeline, LoraLoaderMixin):
 
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
-            logger.warn(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if clean_caption and not is_ftfy_available():
-            logger.warn(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if not isinstance(text, (tuple, list)):

diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py

@@ -460,13 +460,13 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
-            logger.warn(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if clean_caption and not is_ftfy_available():
-            logger.warn(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if not isinstance(text, (tuple, list)):

diffusers/pipelines/deepfloyd_if/pipeline_if_img2img_superresolution.py

@@ -175,7 +175,7 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             )
 
         if unet.config.in_channels != 6:
-            logger.warn(
+            logger.warning(
                 "It seems like you have loaded a checkpoint that shall not be used for super resolution from {unet.config._name_or_path} as it accepts {unet.config.in_channels} input channels instead of 6. Please make sure to pass a super resolution checkpoint as the `'unet'`: IFSuperResolutionPipeline.from_pretrained(unet=super_resolution_unet, ...)`."
             )
 
@@ -209,13 +209,13 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
-            logger.warn(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if clean_caption and not is_ftfy_available():
-            logger.warn(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if not isinstance(text, (tuple, list)):

diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting.py

@@ -500,13 +500,13 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
-            logger.warn(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if clean_caption and not is_ftfy_available():
-            logger.warn(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if not isinstance(text, (tuple, list)):

diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py

@@ -177,7 +177,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             )
 
         if unet.config.in_channels != 6:
-            logger.warn(
+            logger.warning(
                 "It seems like you have loaded a checkpoint that shall not be used for super resolution from {unet.config._name_or_path} as it accepts {unet.config.in_channels} input channels instead of 6. Please make sure to pass a super resolution checkpoint as the `'unet'`: IFSuperResolutionPipeline.from_pretrained(unet=super_resolution_unet, ...)`."
             )
 
@@ -211,13 +211,13 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
-            logger.warn(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if clean_caption and not is_ftfy_available():
-            logger.warn(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if not isinstance(text, (tuple, list)):

diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py

@@ -133,7 +133,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
             )
 
         if unet.config.in_channels != 6:
-            logger.warn(
+            logger.warning(
                 "It seems like you have loaded a checkpoint that shall not be used for super resolution from {unet.config._name_or_path} as it accepts {unet.config.in_channels} input channels instead of 6. Please make sure to pass a super resolution checkpoint as the `'unet'`: IFSuperResolutionPipeline.from_pretrained(unet=super_resolution_unet, ...)`."
             )
 
@@ -167,13 +167,13 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
     # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
     def _text_preprocessing(self, text, clean_caption=False):
         if clean_caption and not is_bs4_available():
-            logger.warn(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if clean_caption and not is_ftfy_available():
-            logger.warn(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
-            logger.warn("Setting `clean_caption` to False...")
+            logger.warning(BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`"))
+            logger.warning("Setting `clean_caption` to False...")
             clean_caption = False
 
         if not isinstance(text, (tuple, list)):