Update txt2panoimg/pipeline_sr.py

txt2panoimg/pipeline_sr.py

@@ -1,8 +1,3 @@
-# Copyright © Alibaba, Inc. and its affiliates.
-# The implementation here is modifed based on diffusers.StableDiffusionControlNetImg2ImgPipeline,
-# originally Apache 2.0 License and public available at
-# https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py
-
 import copy
 import re
 from typing import Any, Callable, Dict, List, Optional, Union
@@ -53,7 +48,6 @@ EXAMPLE_DOC_STRING = """
         ...     width=1536,
         ...     control_image=image,
         ... ).images[0]
-
         ```
 """
 
@@ -141,7 +135,6 @@ def get_prompts_with_weights(pipe: DiffusionPipeline, prompt: List[str],
                              max_length: int):
     r"""
     Tokenize a list of prompts and return its tokens with weights of each token.
-
     No padding, starting or ending token is included.
     """
     tokens = []
@@ -265,9 +258,7 @@ def get_weighted_text_embeddings(
     Prompts can be assigned with local weights using brackets. For example,
     prompt 'A (very beautiful) masterpiece' highlights the words 'very beautiful',
     and the embedding tokens corresponding to the words get multiplied by a constant, 1.1.
-
     Also, to regularize of the embedding, the weighted embedding would be scaled to preserve the original mean.
-
     Args:
         pipe (`DiffusionPipeline`):
             Pipe to provide access to the tokenizer and the text encoder.
@@ -434,13 +425,10 @@ class StableDiffusionControlNetImg2ImgPanoPipeline(
         StableDiffusionControlNetImg2ImgPipeline):
     r"""
     Pipeline for text-to-image generation using Stable Diffusion with ControlNet guidance.
-
     This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
     library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
     In addition the pipeline inherits the following loading methods:
         - *Textual-Inversion*: [`loaders.TextualInversionLoaderMixin.load_textual_inversion`]
-
     Args:
         vae ([`AutoencoderKL`]):
             Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
@@ -610,7 +598,6 @@ class StableDiffusionControlNetImg2ImgPanoPipeline(
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
-
         Args:
             prompt (`str` or `list(int)`):
                 prompt to be encoded
@@ -813,7 +800,6 @@ class StableDiffusionControlNetImg2ImgPanoPipeline(
     ):
         r"""
         Function invoked when calling the pipeline for generation.
-
         Args:
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
@@ -889,9 +875,7 @@ class StableDiffusionControlNetImg2ImgPanoPipeline(
                 you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended.
             context_size ('int', *optional*, defaults to '768'):
                 tiled size when denoise the latents.
-
         Examples:
-
         Returns:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
@@ -906,7 +890,6 @@ class StableDiffusionControlNetImg2ImgPanoPipeline(
             return_dict: bool = True
         ) -> Union[DecoderOutput, torch.FloatTensor]:
             r"""Decode a batch of images using a tiled decoder.
-
             Args:
             When this option is enabled, the VAE will split the input tensor into tiles to compute decoding in several
             steps. This is useful to keep memory use constant regardless of image size. The end result of tiled
@@ -1199,4 +1182,4 @@ class StableDiffusionControlNetImg2ImgPanoPipeline(
             return (image, has_nsfw_concept)
 
         return StableDiffusionPipelineOutput(
-            images=image, nsfw_content_detected=has_nsfw_concept)
+            images=image, nsfw_content_detected=has_nsfw_concept)