docs: correct stated defaults in Chroma pipeline docstrings

docs/source/en/api/pipelines/bria_fibo.md

@@ -16,7 +16,7 @@ Text-to-image models have mastered imagination - but not control. FIBO changes t
 
 FIBO is trained on structured JSON captions up to 1,000+ words and designed to understand and control different visual parameters such as lighting, composition, color, and camera settings, enabling precise and reproducible outputs.
 
-With only 8 billion parameters, FIBO provides a new level of image quality, prompt adherence and proffesional control.
+With only 8 billion parameters, FIBO provides a new level of image quality, prompt adherence and professional control.
 
 FIBO is trained exclusively on a structured prompt and will not work with freeform text prompts.
 you can use the [FIBO-VLM-prompt-to-JSON](https://huggingface.co/briaai/FIBO-VLM-prompt-to-JSON) model or the [FIBO-gemini-prompt-to-JSON](https://huggingface.co/briaai/FIBO-gemini-prompt-to-JSON)  to convert your freeform text prompt to a structured JSON prompt.

docs/source/en/api/pipelines/wan.md

@@ -531,7 +531,7 @@ export_to_video(output, "animated_advanced.mp4", fps=30)
 
 - Try lower `shift` values (`2.0` to `5.0`) for lower resolution videos and higher `shift` values (`7.0` to `12.0`) for higher resolution images.
 
-- Wan 2.1 and 2.2 support using [LightX2V LoRAs](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v) to speed up inference. Using them on Wan 2.2 is slightly more involed. Refer to [this code snippet](https://github.com/huggingface/diffusers/pull/12040#issuecomment-3144185272) to learn more.
+- Wan 2.1 and 2.2 support using [LightX2V LoRAs](https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v) to speed up inference. Using them on Wan 2.2 is slightly more involved. Refer to [this code snippet](https://github.com/huggingface/diffusers/pull/12040#issuecomment-3144185272) to learn more.
 
 - Wan 2.2 has two denoisers. By default, LoRAs are only loaded into the first denoiser. One can set `load_into_transformer_2=True` to load LoRAs into the second denoiser. Refer to [this](https://github.com/huggingface/diffusers/pull/12074#issue-3292620048) and [this](https://github.com/huggingface/diffusers/pull/12074#issuecomment-3155896144) examples to learn more.
 

docs/source/en/optimization/memory.md

@@ -156,7 +156,7 @@ pipeline = StableDiffusionXLPipeline.from_pretrained(
 )
 ```
 
-Diffusers uses the maxmium memory of all devices by default, but if they don't fit on the GPUs, then you'll need to use a single GPU and offload to the CPU with the methods below.
+Diffusers uses the maximum memory of all devices by default, but if they don't fit on the GPUs, then you'll need to use a single GPU and offload to the CPU with the methods below.
 
 - [`~DiffusionPipeline.enable_model_cpu_offload`] only works on a single GPU but a very large model may not fit on it
 - [`~DiffusionPipeline.enable_sequential_cpu_offload`] may work but it is extremely slow and also limited to a single GPU
@@ -470,7 +470,7 @@ apply_layerwise_casting(
 
 ## torch.channels_last
 
-[torch.channels_last](https://pytorch.org/tutorials/intermediate/memory_format_tutorial.html) flips how tensors are stored from `(batch size, channels, height, width)` to `(batch size, heigh, width, channels)`. This aligns the tensors with how the hardware sequentially accesses the tensors stored in memory and avoids skipping around in memory to access the pixel values.
+[torch.channels_last](https://pytorch.org/tutorials/intermediate/memory_format_tutorial.html) flips how tensors are stored from `(batch size, channels, height, width)` to `(batch size, height, width, channels)`. This aligns the tensors with how the hardware sequentially accesses the tensors stored in memory and avoids skipping around in memory to access the pixel values.
 
 Not all operators currently support the channels-last format and may result in worst performance, but it is still worth trying.
 

src/diffusers/guiders/magnitude_aware_guidance.py

@@ -35,7 +35,7 @@ class MagnitudeAwareGuidance(BaseGuidance):
             prompt, while lower values allow for more freedom in generation. Higher values may lead to saturation and
             deterioration of image quality.
         alpha (`float`, defaults to `8.0`):
-            The alpha parameter for the magnitude-aware guidance. Higher values cause more aggressive supression of
+            The alpha parameter for the magnitude-aware guidance. Higher values cause more aggressive suppression of
             guidance scale when the magnitude of the guidance update is large.
         guidance_rescale (`float`, defaults to `0.0`):
             The rescale factor applied to the noise predictions. This is used to improve image quality and fix

src/diffusers/models/attention.py

@@ -1651,7 +1651,7 @@ def forward(
         #
         # The reasoning for the change here is `torch.where` became a bottleneck at some point when golfing memory
         # spikes. It is particularly noticeable when the number of frames is high. My understanding is that this comes
-        # from tensors being copied - which is why we resort to spliting and concatenating here. I've not particularly
+        # from tensors being copied - which is why we resort to splitting and concatenating here. I've not particularly
         # looked into this deeply because other memory optimizations led to more pronounced reductions.
         hidden_states = torch.cat(
             [

src/diffusers/models/attention_dispatch.py

@@ -2070,7 +2070,7 @@ def backward(ctx, grad_outputs):
         return (None, grad_input, None, None)
 
 
-# Below are helper functions to handle abritrary head num and abritrary sequence length for Ulysses Anything Attention.
+# Below are helper functions to handle arbitrary head num and arbitrary sequence length for Ulysses Anything Attention.
 def _maybe_pad_qkv_head(x: torch.Tensor, H: int, group: dist.ProcessGroup) -> tuple[torch.Tensor, int]:
     r"""Maybe pad the head dimension to be divisible by world_size.
     x: torch.Tensor, shape (B, S_LOCAL, H, D) H: int, original global head num return: tuple[torch.Tensor, int], padded

src/diffusers/models/transformers/transformer_ltx2.py

@@ -975,7 +975,7 @@ def prepare_audio_coords(
             start=shift, end=num_frames + shift, step=self.patch_size_t, dtype=torch.float32, device=device
         )
 
-        # 2. Calculate start timstamps in seconds with respect to the original spectrogram grid
+        # 2. Calculate start timestamps in seconds with respect to the original spectrogram grid
         audio_scale_factor = self.scale_factors[0]
         # Scale back to mel spectrogram space
         grid_start_mel = grid_f * audio_scale_factor
@@ -984,7 +984,7 @@ def prepare_audio_coords(
         # Convert mel bins back into seconds
         grid_start_s = grid_start_mel * self.hop_length / self.sampling_rate
 
-        # 3. Calculate start timstamps in seconds with respect to the original spectrogram grid
+        # 3. Calculate start timestamps in seconds with respect to the original spectrogram grid
         grid_end_mel = (grid_f + self.patch_size_t) * audio_scale_factor
         grid_end_mel = (grid_end_mel + self.causal_offset - audio_scale_factor).clip(min=0)
         grid_end_s = grid_end_mel * self.hop_length / self.sampling_rate

src/diffusers/pipelines/chroma/pipeline_chroma.py

@@ -628,14 +628,14 @@ def __call__(
                 The height in pixels of the generated image. This is set to 1024 by default for the best results.
             width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                 The width in pixels of the generated image. This is set to 1024 by default for the best results.
-            num_inference_steps (`int`, *optional*, defaults to 50):
+            num_inference_steps (`int`, *optional*, defaults to 35):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             sigmas (`list[float]`, *optional*):
                 Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                 their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                 will be used.
-            guidance_scale (`float`, *optional*, defaults to 3.5):
+            guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion
                 Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
                 of [Imagen Paper](https://huggingface.co/papers/2205.11487). Guidance scale is enabled by setting

src/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

@@ -698,7 +698,7 @@ def __call__(
                 Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                 their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                 will be used.
-            guidance_scale (`float`, *optional*, defaults to 3.5):
+            guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion
                 Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
                 of [Imagen Paper](https://huggingface.co/papers/2205.11487). Guidance scale is enabled by setting

src/diffusers/pipelines/chroma/pipeline_chroma_inpainting.py

@@ -828,20 +828,20 @@ def __call__(
                 with the same aspect ratio of the image and contains all masked area, and then expand that area based
                 on `padding_mask_crop`. The image and mask_image will then be cropped based on the expanded area before
                 resizing to the original image size for inpainting.
-            num_inference_steps (`int`, *optional*, defaults to 35):
+            num_inference_steps (`int`, *optional*, defaults to 28):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.
             sigmas (`List[float]`, *optional*):
                 Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                 their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                 will be used.
-            guidance_scale (`float`, *optional*, defaults to 3.5):
+            guidance_scale (`float`, *optional*, defaults to 7.0):
                 Guidance scale as defined in [Classifier-Free Diffusion
                 Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
                 of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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.
-            strength (`float, *optional*, defaults to 0.9):
+            strength (`float, *optional*, defaults to 0.6):
                 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
@@ -900,7 +900,7 @@ def __call__(
                 The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                 will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                 `._callback_tensor_inputs` attribute of your pipeline class.
-            max_sequence_length (`int` defaults to 512): Maximum sequence length to use with the `prompt`.
+            max_sequence_length (`int` defaults to 256): Maximum sequence length to use with the `prompt`.
 
         Examples:
 

src/diffusers/pipelines/deprecated/unidiffuser/modeling_uvit.py

@@ -1068,7 +1068,7 @@ def forward(
 
 
         Returns:
-            `tuple`: Returns relevant parts of the model's noise prediction: the first element of the tuple is tbe VAE
+            `tuple`: Returns relevant parts of the model's noise prediction: the first element of the tuple is the VAE
             image embedding, the second element is the CLIP image embedding, and the third element is the CLIP text
             embedding.
         """

src/diffusers/pipelines/ltx2/pipeline_ltx2.py

@@ -271,7 +271,7 @@ def __init__(
         self.vae_temporal_compression_ratio = (
             self.vae.temporal_compression_ratio if getattr(self, "vae", None) is not None else 8
         )
-        # TODO: check whether the MEL compression ratio logic here is corrct
+        # TODO: check whether the MEL compression ratio logic here is correct
         self.audio_vae_mel_compression_ratio = (
             self.audio_vae.mel_compression_ratio if getattr(self, "audio_vae", None) is not None else 4
         )

src/diffusers/pipelines/ltx2/pipeline_ltx2_image2video.py

@@ -274,7 +274,7 @@ def __init__(
         self.vae_temporal_compression_ratio = (
             self.vae.temporal_compression_ratio if getattr(self, "vae", None) is not None else 8
         )
-        # TODO: check whether the MEL compression ratio logic here is corrct
+        # TODO: check whether the MEL compression ratio logic here is correct
         self.audio_vae_mel_compression_ratio = (
             self.audio_vae.mel_compression_ratio if getattr(self, "audio_vae", None) is not None else 4
         )

src/diffusers/pipelines/visualcloze/pipeline_visualcloze_combined.py

@@ -223,7 +223,7 @@ def check_inputs(
                     f"got {type(task_prompt)} and {type(content_prompt)}"
                 )
             if len(content_prompt) != len(task_prompt):
-                raise ValueError("`task_prompt` and `content_prompt` must have the same length whe they are lists.")
+                raise ValueError("`task_prompt` and `content_prompt` must have the same length when they are lists.")
 
             for sample in image:
                 if not isinstance(sample, list) or not isinstance(sample[0], list):

src/diffusers/pipelines/visualcloze/pipeline_visualcloze_generation.py

@@ -442,7 +442,7 @@ def check_inputs(
                     f"got {type(task_prompt)} and {type(content_prompt)}"
                 )
             if len(content_prompt) != len(task_prompt):
-                raise ValueError("`task_prompt` and `content_prompt` must have the same length whe they are lists.")
+                raise ValueError("`task_prompt` and `content_prompt` must have the same length when they are lists.")
 
             for sample in image:
                 if not isinstance(sample, list) or not isinstance(sample[0], list):