Merge branch 'main' into group-offloading-xpu

yao-matrix · web-flow · commit 26aef49a81a6 · 2025-04-25T06:32:30.000+08:00
diff --git a/docs/source/en/api/pipelines/flux.md b/docs/source/en/api/pipelines/flux.md
@@ -347,7 +347,7 @@ image = pipe(
     height=1024,
     prompt="wearing sunglasses",
     negative_prompt="",
-    true_cfg=4.0,
+    true_cfg_scale=4.0,
     generator=torch.Generator().manual_seed(4444),
     ip_adapter_image=image,
 ).images[0]
diff --git a/docs/source/en/api/pipelines/wan.md b/docs/source/en/api/pipelines/wan.md
@@ -24,7 +24,7 @@
 
 ## Generating Videos with Wan 2.1
 
-We will first need to install some addtional dependencies.
+We will first need to install some additional dependencies.
 
 ```shell
 pip install -u ftfy imageio-ffmpeg imageio
diff --git a/docs/source/en/training/cogvideox.md b/docs/source/en/training/cogvideox.md
@@ -216,7 +216,7 @@ Setting the `<ID_TOKEN>` is not necessary. From some limited experimentation, we
 > - The original repository uses a `lora_alpha` of `1`. We found this not suitable in many runs, possibly due to difference in modeling backends and training settings. Our recommendation is to set to the `lora_alpha` to either `rank` or `rank // 2`.
 > - If you're training on data whose captions generate bad results with the original model, a `rank` of 64 and above is good and also the recommendation by the team behind CogVideoX. If the generations are already moderately good on your training captions, a `rank` of 16/32 should work. We found that setting the rank too low, say `4`, is not ideal and doesn't produce promising results.
 > - The authors of CogVideoX recommend 4000 training steps and 100 training videos overall to achieve the best result. While that might yield the best results, we found from our limited experimentation that 2000 steps and 25 videos could also be sufficient.
-> - When using the Prodigy opitimizer for training, one can follow the recommendations from [this](https://huggingface.co/blog/sdxl_lora_advanced_script) blog. Prodigy tends to overfit quickly. From my very limited testing, I found a learning rate of `0.5` to be suitable in addition to `--prodigy_use_bias_correction`, `prodigy_safeguard_warmup` and `--prodigy_decouple`.
+> - When using the Prodigy optimizer for training, one can follow the recommendations from [this](https://huggingface.co/blog/sdxl_lora_advanced_script) blog. Prodigy tends to overfit quickly. From my very limited testing, I found a learning rate of `0.5` to be suitable in addition to `--prodigy_use_bias_correction`, `prodigy_safeguard_warmup` and `--prodigy_decouple`.
 > - The recommended learning rate by the CogVideoX authors and from our experimentation with Adam/AdamW is between `1e-3` and `1e-4` for a dataset of 25+ videos.
 >
 > Note that our testing is not exhaustive due to limited time for exploration. Our recommendation would be to play around with the different knobs and dials to find the best settings for your data.
diff --git a/docs/source/en/training/dreambooth.md b/docs/source/en/training/dreambooth.md
@@ -589,7 +589,7 @@ For stage 2 of DeepFloyd IF with DreamBooth, pay attention to these parameters:
 
 * `--learning_rate=5e-6`, use a lower learning rate with a smaller effective batch size
 * `--resolution=256`, the expected resolution for the upscaler
-* `--train_batch_size=2` and `--gradient_accumulation_steps=6`, to effectively train on images wiht faces requires larger batch sizes
+* `--train_batch_size=2` and `--gradient_accumulation_steps=6`, to effectively train on images with faces requires larger batch sizes
 
 ```bash
 export MODEL_NAME="DeepFloyd/IF-II-L-v1.0"
diff --git a/docs/source/en/training/t2i_adapters.md b/docs/source/en/training/t2i_adapters.md
@@ -89,7 +89,7 @@ Many of the basic and important parameters are described in the [Text-to-image](
 
 As with the script parameters, a walkthrough of the training script is provided in the [Text-to-image](text2image#training-script) training guide. Instead, this guide takes a look at the T2I-Adapter relevant parts of the script.
 
-The training script begins by preparing the dataset. This incudes [tokenizing](https://github.com/huggingface/diffusers/blob/aab6de22c33cc01fb7bc81c0807d6109e2c998c9/examples/t2i_adapter/train_t2i_adapter_sdxl.py#L674) the prompt and [applying transforms](https://github.com/huggingface/diffusers/blob/aab6de22c33cc01fb7bc81c0807d6109e2c998c9/examples/t2i_adapter/train_t2i_adapter_sdxl.py#L714) to the images and conditioning images.
+The training script begins by preparing the dataset. This includes [tokenizing](https://github.com/huggingface/diffusers/blob/aab6de22c33cc01fb7bc81c0807d6109e2c998c9/examples/t2i_adapter/train_t2i_adapter_sdxl.py#L674) the prompt and [applying transforms](https://github.com/huggingface/diffusers/blob/aab6de22c33cc01fb7bc81c0807d6109e2c998c9/examples/t2i_adapter/train_t2i_adapter_sdxl.py#L714) to the images and conditioning images.
 
 ```py
 conditioning_image_transforms = transforms.Compose(
diff --git a/examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py b/examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py
@@ -2181,7 +2181,7 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
                 # Predict the noise residual
                 model_pred = transformer(
                     hidden_states=packed_noisy_model_input,
-                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transforme rmodel (we should not keep it but I want to keep the inputs same for the model for testing)
+                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transformer model (we should not keep it but I want to keep the inputs same for the model for testing)
                     timestep=timesteps / 1000,
                     guidance=guidance,
                     pooled_projections=pooled_prompt_embeds,
diff --git a/examples/community/README.md b/examples/community/README.md
@@ -5381,7 +5381,7 @@ pipe = DiffusionPipeline.from_pretrained(
 # Here we need use pipeline internal unet model
 pipe.unet = pipe.unet_model.from_pretrained(model_id, subfolder="unet", variant="fp16", use_safetensors=True)
 
-# Load aditional layers to the model
+# Load additional layers to the model
 pipe.unet.load_additional_layers(weight_path="proc_data/faithdiff/FaithDiff.bin", dtype=dtype)
 
 # Enable vae tiling
diff --git a/examples/community/dps_pipeline.py b/examples/community/dps_pipeline.py
@@ -312,9 +312,9 @@ def contributions(self, in_length, out_length, scale, kernel, kernel_width, anti
                     # These are the coordinates of the output image
                     out_coordinates = np.arange(1, out_length + 1)
 
-                    # since both scale-factor and output size can be provided simulatneously, perserving the center of the image requires shifting
-                    # the output coordinates. the deviation is because out_length doesn't necesary equal in_length*scale.
-                    # to keep the center we need to subtract half of this deivation so that we get equal margins for boths sides and center is preserved.
+                    # since both scale-factor and output size can be provided simultaneously, preserving the center of the image requires shifting
+                    # the output coordinates. the deviation is because out_length doesn't necessary equal in_length*scale.
+                    # to keep the center we need to subtract half of this deviation so that we get equal margins for both sides and center is preserved.
                     shifted_out_coordinates = out_coordinates - (out_length - in_length * scale) / 2
 
                     # These are the matching positions of the output-coordinates on the input image coordinates.
diff --git a/examples/community/fresco_v2v.py b/examples/community/fresco_v2v.py
@@ -351,7 +351,7 @@ def forward(
             cross_attention_kwargs (`dict`, *optional*):
                 A kwargs dictionary that if specified is passed along to the [`AttnProcessor`].
             added_cond_kwargs: (`dict`, *optional*):
-                A kwargs dictionary containin additional embeddings that if specified are added to the embeddings that
+                A kwargs dictionary containing additional embeddings that if specified are added to the embeddings that
                 are passed along to the UNet blocks.
 
         Returns:
@@ -864,9 +864,9 @@ def get_flow_and_interframe_paras(flow_model, imgs):
 class AttentionControl:
     """
     Control FRESCO-based attention
-    * enable/diable spatial-guided attention
-    * enable/diable temporal-guided attention
-    * enable/diable cross-frame attention
+    * enable/disable spatial-guided attention
+    * enable/disable temporal-guided attention
+    * enable/disable cross-frame attention
     * collect intermediate attention feature (for spatial-guided attention)
     """
 
diff --git a/examples/community/hd_painter.py b/examples/community/hd_painter.py
@@ -34,7 +34,7 @@ def __call__(
         temb: Optional[torch.Tensor] = None,
         scale: float = 1.0,
     ) -> torch.Tensor:
-        # Same as the default AttnProcessor up untill the part where similarity matrix gets saved
+        # Same as the default AttnProcessor up until the part where similarity matrix gets saved
         downscale_factor = self.mask_resoltuion // hidden_states.shape[1]
         residual = hidden_states
 
diff --git a/examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py b/examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py
@@ -889,7 +889,7 @@ def main(args):
         mixed_precision=args.mixed_precision,
         log_with=args.report_to,
         project_config=accelerator_project_config,
-        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be devide by the number of processes assuming batches are multiplied by the number of processes
+        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be divided by the number of processes assuming batches are multiplied by the number of processes
     )
 
     # Make one log on every process with the configuration for debugging.
diff --git a/examples/consistency_distillation/train_lcm_distill_lora_sdxl.py b/examples/consistency_distillation/train_lcm_distill_lora_sdxl.py
@@ -721,7 +721,7 @@ def main(args):
         mixed_precision=args.mixed_precision,
         log_with=args.report_to,
         project_config=accelerator_project_config,
-        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be devide by the number of processes assuming batches are multiplied by the number of processes
+        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be divided by the number of processes assuming batches are multiplied by the number of processes
     )
 
     # Make one log on every process with the configuration for debugging.
diff --git a/examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py b/examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py
@@ -884,7 +884,7 @@ def main(args):
         mixed_precision=args.mixed_precision,
         log_with=args.report_to,
         project_config=accelerator_project_config,
-        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be devide by the number of processes assuming batches are multiplied by the number of processes
+        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be divided by the number of processes assuming batches are multiplied by the number of processes
     )
 
     # Make one log on every process with the configuration for debugging.
diff --git a/examples/consistency_distillation/train_lcm_distill_sd_wds.py b/examples/consistency_distillation/train_lcm_distill_sd_wds.py
@@ -854,7 +854,7 @@ def main(args):
         mixed_precision=args.mixed_precision,
         log_with=args.report_to,
         project_config=accelerator_project_config,
-        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be devide by the number of processes assuming batches are multiplied by the number of processes
+        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be divided by the number of processes assuming batches are multiplied by the number of processes
     )
 
     # Make one log on every process with the configuration for debugging.
diff --git a/examples/consistency_distillation/train_lcm_distill_sdxl_wds.py b/examples/consistency_distillation/train_lcm_distill_sdxl_wds.py
@@ -894,7 +894,7 @@ def main(args):
         mixed_precision=args.mixed_precision,
         log_with=args.report_to,
         project_config=accelerator_project_config,
-        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be devide by the number of processes assuming batches are multiplied by the number of processes
+        split_batches=True,  # It's important to set this to True when using webdataset to get the right number of steps for lr scheduling. If set to False, the number of steps will be divided by the number of processes assuming batches are multiplied by the number of processes
     )
 
     # Make one log on every process with the configuration for debugging.
diff --git a/examples/dreambooth/train_dreambooth_flux.py b/examples/dreambooth/train_dreambooth_flux.py
@@ -1634,7 +1634,7 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
                 # Predict the noise residual
                 model_pred = transformer(
                     hidden_states=packed_noisy_model_input,
-                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transforme rmodel (we should not keep it but I want to keep the inputs same for the model for testing)
+                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transformer model (we should not keep it but I want to keep the inputs same for the model for testing)
                     timestep=timesteps / 1000,
                     guidance=guidance,
                     pooled_projections=pooled_prompt_embeds,
diff --git a/examples/dreambooth/train_dreambooth_lora_flux.py b/examples/dreambooth/train_dreambooth_lora_flux.py
@@ -1749,7 +1749,7 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
                 # Predict the noise residual
                 model_pred = transformer(
                     hidden_states=packed_noisy_model_input,
-                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transforme rmodel (we should not keep it but I want to keep the inputs same for the model for testing)
+                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transformer model (we should not keep it but I want to keep the inputs same for the model for testing)
                     timestep=timesteps / 1000,
                     guidance=guidance,
                     pooled_projections=pooled_prompt_embeds,
diff --git a/examples/research_projects/flux_lora_quantization/train_dreambooth_lora_flux_miniature.py b/examples/research_projects/flux_lora_quantization/train_dreambooth_lora_flux_miniature.py
@@ -1088,7 +1088,7 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
                 text_ids = batch["text_ids"].to(device=accelerator.device, dtype=weight_dtype)
                 model_pred = transformer(
                     hidden_states=packed_noisy_model_input,
-                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transforme rmodel (we should not keep it but I want to keep the inputs same for the model for testing)
+                    # YiYi notes: divide it by 1000 for now because we scale it by 1000 in the transformer model (we should not keep it but I want to keep the inputs same for the model for testing)
                     timestep=timesteps / 1000,
                     guidance=guidance,
                     pooled_projections=pooled_prompt_embeds,
diff --git a/src/diffusers/models/downsampling.py b/src/diffusers/models/downsampling.py
@@ -286,7 +286,7 @@ def forward(self, inputs: torch.Tensor) -> torch.Tensor:
 
 
 class CogVideoXDownsample3D(nn.Module):
-    # Todo: Wait for paper relase.
+    # Todo: Wait for paper release.
     r"""
     A 3D Downsampling layer using in [CogVideoX]() by Tsinghua University & ZhipuAI
 
diff --git a/src/diffusers/models/upsampling.py b/src/diffusers/models/upsampling.py
@@ -358,7 +358,7 @@ def forward(self, inputs: torch.Tensor) -> torch.Tensor:
 
 class CogVideoXUpsample3D(nn.Module):
     r"""
-    A 3D Upsample layer using in CogVideoX by Tsinghua University & ZhipuAI # Todo: Wait for paper relase.
+    A 3D Upsample layer using in CogVideoX by Tsinghua University & ZhipuAI # Todo: Wait for paper release.
 
     Args:
         in_channels (`int`):
diff --git a/src/diffusers/pipelines/allegro/pipeline_allegro.py b/src/diffusers/pipelines/allegro/pipeline_allegro.py
@@ -514,7 +514,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/deepfloyd_if/pipeline_if.py b/src/diffusers/pipelines/deepfloyd_if/pipeline_if.py
@@ -484,7 +484,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py b/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py
@@ -528,7 +528,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img_superresolution.py b/src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img_superresolution.py
@@ -281,7 +281,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting.py b/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting.py
@@ -568,7 +568,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py b/src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py
@@ -283,7 +283,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py b/src/diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py
@@ -239,7 +239,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_model_editing.py b/src/diffusers/pipelines/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_model_editing.py
@@ -574,7 +574,7 @@ def edit_model(
                 idxs_replace.append(76)
             idxs_replaces.append(idxs_replace)
 
-        # prepare batch: for each pair of setences, old context and new values
+        # prepare batch: for each pair of sentences, old context and new values
         contexts, valuess = [], []
         for old_emb, new_emb, idxs_replace in zip(old_embs, new_embs, idxs_replaces):
             context = old_emb.detach()
diff --git a/src/diffusers/pipelines/latte/pipeline_latte.py b/src/diffusers/pipelines/latte/pipeline_latte.py
@@ -501,7 +501,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/lumina/pipeline_lumina.py b/src/diffusers/pipelines/lumina/pipeline_lumina.py
@@ -534,7 +534,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/pag/pipeline_pag_pixart_sigma.py b/src/diffusers/pipelines/pag/pipeline_pag_pixart_sigma.py
@@ -488,7 +488,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/pag/pipeline_pag_sana.py b/src/diffusers/pipelines/pag/pipeline_pag_sana.py
@@ -524,7 +524,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/pixart_alpha/pipeline_pixart_alpha.py b/src/diffusers/pipelines/pixart_alpha/pipeline_pixart_alpha.py
@@ -598,7 +598,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/pixart_alpha/pipeline_pixart_sigma.py b/src/diffusers/pipelines/pixart_alpha/pipeline_pixart_sigma.py
@@ -525,7 +525,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/sana/pipeline_sana.py b/src/diffusers/pipelines/sana/pipeline_sana.py
@@ -600,7 +600,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py b/src/diffusers/pipelines/sana/pipeline_sana_controlnet.py
@@ -615,7 +615,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/sana/pipeline_sana_sprint.py b/src/diffusers/pipelines/sana/pipeline_sana_sprint.py
@@ -491,7 +491,7 @@ def _clean_caption(self, caption):
         # &amp
         caption = re.sub(r"&amp", "", caption)
 
-        # ip adresses:
+        # ip addresses:
         caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)
 
         # article ids:
diff --git a/src/diffusers/pipelines/stable_diffusion_gligen/pipeline_stable_diffusion_gligen_text_image.py b/src/diffusers/pipelines/stable_diffusion_gligen/pipeline_stable_diffusion_gligen_text_image.py
diff --git a/src/diffusers/pipelines/wan/pipeline_wan.py b/src/diffusers/pipelines/wan/pipeline_wan.py
diff --git a/src/diffusers/pipelines/wan/pipeline_wan_i2v.py b/src/diffusers/pipelines/wan/pipeline_wan_i2v.py
diff --git a/src/diffusers/pipelines/wan/pipeline_wan_video2video.py b/src/diffusers/pipelines/wan/pipeline_wan_video2video.py
diff --git a/src/diffusers/schedulers/scheduling_deis_multistep.py b/src/diffusers/schedulers/scheduling_deis_multistep.py
diff --git a/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py b/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
diff --git a/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py b/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py
diff --git a/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py b/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
diff --git a/src/diffusers/schedulers/scheduling_sasolver.py b/src/diffusers/schedulers/scheduling_sasolver.py
diff --git a/src/diffusers/schedulers/scheduling_unipc_multistep.py b/src/diffusers/schedulers/scheduling_unipc_multistep.py

Original file line number	Diff line number	Diff line change
@@ -216,7 +216,7 @@ Setting the `<ID_TOKEN>` is not necessary. From some limited experimentation, we
`216`	`216`	> - The original repository uses a `lora_alpha` of `1`. We found this not suitable in many runs, possibly due to difference in modeling backends and training settings. Our recommendation is to set to the `lora_alpha` to either `rank` or `rank // 2`.
`217`	`217`	> - If you're training on data whose captions generate bad results with the original model, a `rank` of 64 and above is good and also the recommendation by the team behind CogVideoX. If the generations are already moderately good on your training captions, a `rank` of 16/32 should work. We found that setting the rank too low, say `4`, is not ideal and doesn't produce promising results.
`218`	`218`	`> - The authors of CogVideoX recommend 4000 training steps and 100 training videos overall to achieve the best result. While that might yield the best results, we found from our limited experimentation that 2000 steps and 25 videos could also be sufficient.`
`219`		-> - When using the Prodigy opitimizer for training, one can follow the recommendations from [this](https://huggingface.co/blog/sdxl_lora_advanced_script) blog. Prodigy tends to overfit quickly. From my very limited testing, I found a learning rate of `0.5` to be suitable in addition to `--prodigy_use_bias_correction`, `prodigy_safeguard_warmup` and `--prodigy_decouple`.
	`219`	+> - When using the Prodigy optimizer for training, one can follow the recommendations from [this](https://huggingface.co/blog/sdxl_lora_advanced_script) blog. Prodigy tends to overfit quickly. From my very limited testing, I found a learning rate of `0.5` to be suitable in addition to `--prodigy_use_bias_correction`, `prodigy_safeguard_warmup` and `--prodigy_decouple`.
`220`	`220`	> - The recommended learning rate by the CogVideoX authors and from our experimentation with Adam/AdamW is between `1e-3` and `1e-4` for a dataset of 25+ videos.
`221`	`221`	`>`
`222`	`222`	`> Note that our testing is not exhaustive due to limited time for exploration. Our recommendation would be to play around with the different knobs and dials to find the best settings for your data.`