Add "Copied from" statements in comments

huggingface · Dec 1, 2023 · 4a6e40e · 4a6e40e
1 parent 284fc82
commit 4a6e40e
Showing 1 changed file with 20 additions and 0 deletions.
diff --git a/examples/community/llm_grounded_diffusion.py b/examples/community/llm_grounded_diffusion.py
@@ -1308,20 +1308,24 @@ def latent_lmd_guidance(
 
     # Below are methods copied from StableDiffusionPipeline
     # The design choice of not inheriting from StableDiffusionPipeline is discussed here: https://github.com/huggingface/diffusers/pull/5993#issuecomment-1834258517
+
+    # 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
@@ -1330,13 +1334,15 @@ def enable_vae_tiling(self):
         """
         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.pipeline_stable_diffusion.StableDiffusionPipeline._encode_prompt
     def _encode_prompt(
         self,
         prompt,
@@ -1371,6 +1377,7 @@ def _encode_prompt(
 
         return prompt_embeds
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_prompt
     def encode_prompt(
         self,
         prompt,
@@ -1576,6 +1583,7 @@ def encode_prompt(
 
         return prompt_embeds, negative_prompt_embeds
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
     def encode_image(self, image, device, num_images_per_prompt):
         dtype = next(self.image_encoder.parameters()).dtype
 
@@ -1591,6 +1599,7 @@ def encode_image(self, image, device, num_images_per_prompt):
         uncond_image_embeds = torch.zeros_like(image_embeds)
         return image_embeds, uncond_image_embeds
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
     def run_safety_checker(self, image, device, dtype):
         if self.safety_checker is None:
             has_nsfw_concept = None
@@ -1611,6 +1620,7 @@ def run_safety_checker(self, image, device, dtype):
             )
         return image, has_nsfw_concept
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.decode_latents
     def decode_latents(self, latents):
         deprecation_message = "The decode_latents method is deprecated and will be removed in 1.0.0. Please use VaeImageProcessor.postprocess(...) instead"
         deprecate("decode_latents", "1.0.0",
@@ -1623,6 +1633,7 @@ def decode_latents(self, latents):
         image = image.cpu().permute(0, 2, 3, 1).float().numpy()
         return image
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
     def prepare_extra_step_kwargs(self, generator, eta):
         # 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.
@@ -1644,6 +1655,7 @@ def prepare_extra_step_kwargs(self, generator, eta):
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(
         self,
         batch_size,
@@ -1678,6 +1690,7 @@ def prepare_latents(
         latents = latents * self.scheduler.init_noise_sigma
         return latents
 
+    # 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.
 
@@ -1700,6 +1713,7 @@ def enable_freeu(self, s1: float, s2: float, b1: float, b2: float):
             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_vae_tiling
     def disable_freeu(self):
         """Disables the FreeU mechanism if enabled."""
         self.unet.disable_freeu()
@@ -1733,29 +1747,35 @@ def get_guidance_scale_embedding(self, w, embedding_dim=512, dtype=torch.float32
         assert emb.shape == (w.shape[0], embedding_dim)
         return emb
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.guidance_scale
     @property
     def guidance_scale(self):
         return self._guidance_scale
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.guidance_rescale
     @property
     def guidance_rescale(self):
         return self._guidance_rescale
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.clip_skip
     @property
     def clip_skip(self):
         return self._clip_skip
 
     # 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.
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.do_classifier_free_guidance
     @property
     def do_classifier_free_guidance(self):
         return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.cross_attention_kwargs
     @property
     def cross_attention_kwargs(self):
         return self._cross_attention_kwargs
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.num_timesteps
     @property
     def num_timesteps(self):
         return self._num_timesteps