fix

Author: stevhliu

src/diffusers/pipelines/marigold/pipeline_marigold_depth.py

@@ -86,12 +86,9 @@ class MarigoldDepthOutput(BaseOutput):
 
     Args:
         prediction (`np.ndarray`, `torch.Tensor`):
-            Predicted depth maps with values in the range [0, 1]. The shape is $numimages \times 1 \times height \times
-            width$ for `torch.Tensor` or $numimages \times height \times width \times 1$ for `np.ndarray`.
+            Predicted depth maps with values in the range [0, 1]. The shape is $numimages \times 1 \times height \times width$ for `torch.Tensor` or $numimages \times height \times width \times 1$ for `np.ndarray`.
         uncertainty (`None`, `np.ndarray`, `torch.Tensor`):
-            Uncertainty maps computed from the ensemble, with values in the range [0, 1]. The shape is $numimages
-            \times 1 \times height \times width$ for `torch.Tensor` or $numimages \times height \times width \times 1$
-            for `np.ndarray`.
+            Uncertainty maps computed from the ensemble, with values in the range [0, 1]. The shape is $numimages \times 1 \times height \times width$ for `torch.Tensor` or $numimages \times height \times width \times 1$ for `np.ndarray`.
         latent (`None`, `torch.Tensor`):
             Latent features corresponding to the predictions, compatible with the `latents` argument of the pipeline.
             The shape is $numimages * numensemble \times 4 \times latentheight \times latentwidth$.

src/diffusers/pipelines/marigold/pipeline_marigold_intrinsics.py

@@ -99,14 +99,9 @@ class MarigoldIntrinsicsOutput(BaseOutput):
 
     Args:
         prediction (`np.ndarray`, `torch.Tensor`):
-            Predicted image intrinsics with values in the range [0, 1]. The shape is $(numimages * numtargets) \times 3
-            \times height \times width$ for `torch.Tensor` or $(numimages * numtargets) \times height \times width
-            \times 3$ for `np.ndarray`, where `numtargets` corresponds to the number of predicted target modalities of
-            the intrinsic image decomposition.
+            Predicted image intrinsics with values in the range [0, 1]. The shape is $(numimages * numtargets) \times 3 \times height \times width$ for `torch.Tensor` or $(numimages * numtargets) \times height \times width \times 3$ for `np.ndarray`, where `numtargets` corresponds to the number of predicted target modalities of the intrinsic image decomposition.
         uncertainty (`None`, `np.ndarray`, `torch.Tensor`):
-            Uncertainty maps computed from the ensemble, with values in the range [0, 1]. The shape is $(numimages *
-            numtargets) \times 3 \times height \times width$ for `torch.Tensor` or $(numimages * numtargets) \times
-            height \times width \times 3$ for `np.ndarray`.
+            Uncertainty maps computed from the ensemble, with values in the range [0, 1]. The shape is $(numimages * numtargets) \times 3 \times height \times width$ for `torch.Tensor` or $(numimages * numtargets) \times height \times width \times 3$ for `np.ndarray`.
         latent (`None`, `torch.Tensor`):
             Latent features corresponding to the predictions, compatible with the `latents` argument of the pipeline.
             The shape is $(numimages * numensemble) \times (numtargets * 4) \times latentheight \times latentwidth$.

src/diffusers/pipelines/marigold/pipeline_marigold_normals.py

@@ -81,12 +81,9 @@ class MarigoldNormalsOutput(BaseOutput):
 
     Args:
         prediction (`np.ndarray`, `torch.Tensor`):
-            Predicted normals with values in the range [-1, 1]. The shape is $numimages \times 3 \times height \times
-            width$ for `torch.Tensor` or $numimages \times height \times width \times 3$ for `np.ndarray`.
+            Predicted normals with values in the range [-1, 1]. The shape is $numimages \times 3 \times height \times width$ for `torch.Tensor` or $numimages \times height \times width \times 3$ for `np.ndarray`.
         uncertainty (`None`, `np.ndarray`, `torch.Tensor`):
-            Uncertainty maps computed from the ensemble, with values in the range [0, 1]. The shape is $numimages
-            \times 1 \times height \times width$ for `torch.Tensor` or $numimages \times height \times width \times 1$
-            for `np.ndarray`.
+            Uncertainty maps computed from the ensemble, with values in the range [0, 1]. The shape is $numimages \times 1 \times height \times width$ for `torch.Tensor` or $numimages \times height \times width \times 1$ for `np.ndarray`.
         latent (`None`, `torch.Tensor`):
             Latent features corresponding to the predictions, compatible with the `latents` argument of the pipeline.
             The shape is $numimages * numensemble \times 4 \times latentheight \times latentwidth$.