Merge branch 'main' into ltx-2-transformer

Author: sayakpaul

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

@@ -250,9 +250,6 @@ The code snippets available in [this](https://github.com/huggingface/diffusers/p
 
 The general rule of thumb to keep in mind when preparing inputs for the VACE pipeline is that the input images, or frames of a video that you want to use for conditioning, should have a corresponding mask that is black in color. The black mask signifies that the model will not generate new content for that area, and only use those parts for conditioning the generation process. For parts/frames that should be generated by the model, the mask should be white in color.
 
-</hfoption>
-</hfoptions>
-
 ### Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
 
 [Wan-Animate](https://huggingface.co/papers/2509.14055) by the Wan Team.

docs/source/en/quantization/torchao.md

@@ -33,7 +33,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )
@@ -50,7 +50,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )
@@ -70,7 +70,7 @@ pipeline_quant_config = PipelineQuantizationConfig(
 )
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
-    quantzation_config=pipeline_quant_config,
+    quantization_config=pipeline_quant_config,
     torch_dtype=torch.bfloat16,
     device_map="cuda"
 )

src/diffusers/modular_pipelines/mellon_node_utils.py

@@ -168,6 +168,14 @@ def num_inference_steps(cls, default: int = 25) -> "MellonParam":
             name="num_inference_steps", label="Steps", type="int", default=default, min=1, max=100, display="slider"
         )
 
+    @classmethod
+    def num_frames(cls, default: int = 81) -> "MellonParam":
+        return cls(name="num_frames", label="Frames", type="int", default=default, min=1, max=480, display="slider")
+
+    @classmethod
+    def videos(cls) -> "MellonParam":
+        return cls(name="videos", label="Videos", type="video", display="output")
+
     @classmethod
     def vae(cls) -> "MellonParam":
         """

src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py

@@ -143,7 +143,20 @@ def set_begin_index(self, begin_index: int = 0):
         self._begin_index = begin_index
 
     # Copied from diffusers.schedulers.scheduling_edm_euler.EDMEulerScheduler.precondition_inputs
-    def precondition_inputs(self, sample, sigma):
+    def precondition_inputs(self, sample: torch.Tensor, sigma: Union[float, torch.Tensor]) -> torch.Tensor:
+        """
+        Precondition the input sample by scaling it according to the EDM formulation.
+
+        Args:
+            sample (`torch.Tensor`):
+                The input sample tensor to precondition.
+            sigma (`float` or `torch.Tensor`):
+                The current sigma (noise level) value.
+
+        Returns:
+            `torch.Tensor`:
+                The scaled input sample.
+        """
         c_in = self._get_conditioning_c_in(sigma)
         scaled_sample = sample * c_in
         return scaled_sample
@@ -155,7 +168,27 @@ def precondition_noise(self, sigma):
         return sigma.atan() / math.pi * 2
 
     # Copied from diffusers.schedulers.scheduling_edm_euler.EDMEulerScheduler.precondition_outputs
-    def precondition_outputs(self, sample, model_output, sigma):
+    def precondition_outputs(
+        self,
+        sample: torch.Tensor,
+        model_output: torch.Tensor,
+        sigma: Union[float, torch.Tensor],
+    ) -> torch.Tensor:
+        """
+        Precondition the model outputs according to the EDM formulation.
+
+        Args:
+            sample (`torch.Tensor`):
+                The input sample tensor.
+            model_output (`torch.Tensor`):
+                The direct output from the learned diffusion model.
+            sigma (`float` or `torch.Tensor`):
+                The current sigma (noise level) value.
+
+        Returns:
+            `torch.Tensor`:
+                The denoised sample computed by combining the skip connection and output scaling.
+        """
         sigma_data = self.config.sigma_data
         c_skip = sigma_data**2 / (sigma**2 + sigma_data**2)
 
@@ -173,13 +206,13 @@ def precondition_outputs(self, sample, model_output, sigma):
     # Copied from diffusers.schedulers.scheduling_edm_euler.EDMEulerScheduler.scale_model_input
     def scale_model_input(self, sample: torch.Tensor, timestep: Union[float, torch.Tensor]) -> torch.Tensor:
         """
-        Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
-        current timestep. Scales the denoising model input by `(sigma**2 + 1) ** 0.5` to match the Euler algorithm.
+        Scale the denoising model input to match the Euler algorithm. Ensures interchangeability with schedulers that
+        need to scale the denoising model input depending on the current timestep.
 
         Args:
             sample (`torch.Tensor`):
-                The input sample.
-            timestep (`int`, *optional*):
+                The input sample tensor.
+            timestep (`float` or `torch.Tensor`):
                 The current timestep in the diffusion chain.
 
         Returns:
@@ -242,8 +275,27 @@ def set_timesteps(self, num_inference_steps: int = None, device: Union[str, torc
         self.noise_sampler = None
 
     # Copied from diffusers.schedulers.scheduling_edm_euler.EDMEulerScheduler._compute_karras_sigmas
-    def _compute_karras_sigmas(self, ramp, sigma_min=None, sigma_max=None) -> torch.Tensor:
-        """Constructs the noise schedule of Karras et al. (2022)."""
+    def _compute_karras_sigmas(
+        self,
+        ramp: torch.Tensor,
+        sigma_min: Optional[float] = None,
+        sigma_max: Optional[float] = None,
+    ) -> torch.Tensor:
+        """
+        Construct the noise schedule of [Karras et al. (2022)](https://huggingface.co/papers/2206.00364).
+
+        Args:
+            ramp (`torch.Tensor`):
+                A tensor of values in [0, 1] representing the interpolation positions.
+            sigma_min (`float`, *optional*):
+                Minimum sigma value. If `None`, uses `self.config.sigma_min`.
+            sigma_max (`float`, *optional*):
+                Maximum sigma value. If `None`, uses `self.config.sigma_max`.
+
+        Returns:
+            `torch.Tensor`:
+                The computed Karras sigma schedule.
+        """
         sigma_min = sigma_min or self.config.sigma_min
         sigma_max = sigma_max or self.config.sigma_max
 
@@ -254,10 +306,27 @@ def _compute_karras_sigmas(self, ramp, sigma_min=None, sigma_max=None) -> torch.
         return sigmas
 
     # Copied from diffusers.schedulers.scheduling_edm_euler.EDMEulerScheduler._compute_exponential_sigmas
-    def _compute_exponential_sigmas(self, ramp, sigma_min=None, sigma_max=None) -> torch.Tensor:
-        """Implementation closely follows k-diffusion.
-
+    def _compute_exponential_sigmas(
+        self,
+        ramp: torch.Tensor,
+        sigma_min: Optional[float] = None,
+        sigma_max: Optional[float] = None,
+    ) -> torch.Tensor:
+        """
+        Compute the exponential sigma schedule. Implementation closely follows k-diffusion:
         https://github.com/crowsonkb/k-diffusion/blob/6ab5146d4a5ef63901326489f31f1d8e7dd36b48/k_diffusion/sampling.py#L26
+
+        Args:
+            ramp (`torch.Tensor`):
+                A tensor of values representing the interpolation positions.
+            sigma_min (`float`, *optional*):
+                Minimum sigma value. If `None`, uses `self.config.sigma_min`.
+            sigma_max (`float`, *optional*):
+                Maximum sigma value. If `None`, uses `self.config.sigma_max`.
+
+        Returns:
+            `torch.Tensor`:
+                The computed exponential sigma schedule.
         """
         sigma_min = sigma_min or self.config.sigma_min
         sigma_max = sigma_max or self.config.sigma_max
@@ -354,7 +423,10 @@ def dpm_solver_first_order_update(
             `torch.Tensor`:
                 The sample tensor at the previous timestep.
         """
-        sigma_t, sigma_s = self.sigmas[self.step_index + 1], self.sigmas[self.step_index]
+        sigma_t, sigma_s = (
+            self.sigmas[self.step_index + 1],
+            self.sigmas[self.step_index],
+        )
         alpha_t, sigma_t = self._sigma_to_alpha_sigma_t(sigma_t)
         alpha_s, sigma_s = self._sigma_to_alpha_sigma_t(sigma_s)
         lambda_t = torch.log(alpha_t) - torch.log(sigma_t)
@@ -540,7 +612,10 @@ def step(
                     [g.initial_seed() for g in generator] if isinstance(generator, list) else generator.initial_seed()
                 )
             self.noise_sampler = BrownianTreeNoiseSampler(
-                model_output, sigma_min=self.config.sigma_min, sigma_max=self.config.sigma_max, seed=seed
+                model_output,
+                sigma_min=self.config.sigma_min,
+                sigma_max=self.config.sigma_max,
+                seed=seed,
             )
         noise = self.noise_sampler(self.sigmas[self.step_index], self.sigmas[self.step_index + 1]).to(
             model_output.device
@@ -612,7 +687,18 @@ def add_noise(
         return noisy_samples
 
     # Copied from diffusers.schedulers.scheduling_edm_euler.EDMEulerScheduler._get_conditioning_c_in
-    def _get_conditioning_c_in(self, sigma):
+    def _get_conditioning_c_in(self, sigma: Union[float, torch.Tensor]) -> Union[float, torch.Tensor]:
+        """
+        Compute the input conditioning factor for the EDM formulation.
+
+        Args:
+            sigma (`float` or `torch.Tensor`):
+                The current sigma (noise level) value.
+
+        Returns:
+            `float` or `torch.Tensor`:
+                The input conditioning factor `c_in`.
+        """
         c_in = 1 / ((sigma**2 + self.config.sigma_data**2) ** 0.5)
         return c_in