diff --git a/test/test_transforms_v2.py b/test/test_transforms_v2.py
index 6d9f9732552..69a2dec48c9 100644
--- a/test/test_transforms_v2.py
+++ b/test/test_transforms_v2.py
@@ -4142,9 +4142,21 @@ def adapter(_, input, __):
 
         check_transform(transforms.GaussianNoise(), make_input(dtype=torch.uint8), check_sample_input=adapter)
 
+    def test_pil_image(self):
+        image = make_image_pil()
+        out = F.gaussian_noise(image)
+        assert isinstance(out, PIL.Image.Image)
+        assert out.mode == image.mode
+        assert out.size == image.size
+
+        out = F.gaussian_noise(image, mean=100, clip=True)
+        assert isinstance(out, PIL.Image.Image)
+        assert out.mode == image.mode
+        assert out.size == image.size
+        assert F.pil_to_tensor(out).min() >= 0
+        assert F.pil_to_tensor(out).max() <= 255
+
     def test_bad_input(self):
-        with pytest.raises(ValueError, match="Gaussian Noise is not implemented for PIL images."):
-            F.gaussian_noise(make_image_pil())
         with pytest.raises(ValueError, match="Input tensor is expected to be in uint8 or float dtype"):
             F.gaussian_noise(make_image(dtype=torch.int32))
         with pytest.raises(ValueError, match="sigma shouldn't be negative"):
diff --git a/torchvision/transforms/v2/_misc.py b/torchvision/transforms/v2/_misc.py
index 305149c87b1..32229ee0a64 100644
--- a/torchvision/transforms/v2/_misc.py
+++ b/torchvision/transforms/v2/_misc.py
@@ -223,8 +223,8 @@ class GaussianNoise(Transform):
     noise added to each image will be different.
 
     The input tensor is also expected to be of float dtype in ``[0, 1]``,
-    or of ``uint8`` dtype in ``[0, 255]``. This transform does not support PIL
-    images.
+    or of ``uint8`` dtype in ``[0, 255]``. PIL images are supported and
+    processed through the ``uint8`` path via ``pil_to_tensor``.
 
     Regardless of the dtype used, the parameters of the function use the same
     scale, so a ``mean`` parameter of 0.5 will result in an average value
diff --git a/torchvision/transforms/v2/functional/_misc.py b/torchvision/transforms/v2/functional/_misc.py
index 55d085a2e24..cb9d7bf8701 100644
--- a/torchvision/transforms/v2/functional/_misc.py
+++ b/torchvision/transforms/v2/functional/_misc.py
@@ -226,9 +226,11 @@ def gaussian_noise_video(video: torch.Tensor, mean: float = 0.0, sigma: float =
 
 @_register_kernel_internal(gaussian_noise, PIL.Image.Image)
 def _gaussian_noise_pil(
-    video: torch.Tensor, mean: float = 0.0, sigma: float = 0.1, clip: bool = True
+    image: PIL.Image.Image, mean: float = 0.0, sigma: float = 0.1, clip: bool = True
 ) -> PIL.Image.Image:
-    raise ValueError("Gaussian Noise is not implemented for PIL images.")
+    t_img = pil_to_tensor(image)
+    output = gaussian_noise_image(t_img, mean=mean, sigma=sigma, clip=clip)
+    return to_pil_image(output, mode=image.mode)
 
 
 def to_dtype(inpt: torch.Tensor, dtype: torch.dtype = torch.float, scale: bool = False) -> torch.Tensor: