diff --git a/src/diffusers/pipelines/z_image/pipeline_z_image.py b/src/diffusers/pipelines/z_image/pipeline_z_image.py
index 3e2055c6257f..adb2480756ec 100644
--- a/src/diffusers/pipelines/z_image/pipeline_z_image.py
+++ b/src/diffusers/pipelines/z_image/pipeline_z_image.py
@@ -339,10 +339,9 @@ def __call__(
                 will be used.
             guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). 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.
+                Z-Image uses the formula `pred = pos + guidance_scale * (pos - neg)`, so guidance scale is enabled
+                by setting `guidance_scale > 0`. Higher guidance scale encourages to generate images that are closely
+                linked to the text `prompt`, usually at the expense of lower image quality.
             cfg_normalization (`bool`, *optional*, defaults to False):
                 Whether to apply configuration normalization.
             cfg_truncation (`float`, *optional*, defaults to 1.0):
diff --git a/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet.py b/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet.py
index 81373ffb56ff..b5ce08fdc46c 100644
--- a/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet.py
+++ b/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet.py
@@ -431,10 +431,9 @@ def __call__(
                 will be used.
             guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). 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.
+                Z-Image uses the formula `pred = pos + guidance_scale * (pos - neg)`, so guidance scale is enabled
+                by setting `guidance_scale > 0`. Higher guidance scale encourages to generate images that are closely
+                linked to the text `prompt`, usually at the expense of lower image quality.
             control_image (`PipelineImageInput`):
                 The ControlNet input condition to provide guidance to the `transformer` for generation. If the type is
                 specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
diff --git a/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet_inpaint.py b/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet_inpaint.py
index 178e74dea4fa..28183a89922c 100644
--- a/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet_inpaint.py
+++ b/src/diffusers/pipelines/z_image/pipeline_z_image_controlnet_inpaint.py
@@ -440,10 +440,9 @@ def __call__(
                 will be used.
             guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). 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.
+                Z-Image uses the formula `pred = pos + guidance_scale * (pos - neg)`, so guidance scale is enabled
+                by setting `guidance_scale > 0`. Higher guidance scale encourages to generate images that are closely
+                linked to the text `prompt`, usually at the expense of lower image quality.
             image (`PipelineImageInput`):
                 `Image`, numpy array or tensor representing an image batch to be inpainted (which parts of the image to
                 be masked out with `mask_image` and repainted according to `prompt`).
diff --git a/src/diffusers/pipelines/z_image/pipeline_z_image_img2img.py b/src/diffusers/pipelines/z_image/pipeline_z_image_img2img.py
index b5c7740bb0c1..9c198f3abd9d 100644
--- a/src/diffusers/pipelines/z_image/pipeline_z_image_img2img.py
+++ b/src/diffusers/pipelines/z_image/pipeline_z_image_img2img.py
@@ -424,10 +424,9 @@ def __call__(
                 will be used.
             guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). 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.
+                Z-Image uses the formula `pred = pos + guidance_scale * (pos - neg)`, so guidance scale is enabled
+                by setting `guidance_scale > 0`. Higher guidance scale encourages to generate images that are closely
+                linked to the text `prompt`, usually at the expense of lower image quality.
             cfg_normalization (`bool`, *optional*, defaults to False):
                 Whether to apply configuration normalization.
             cfg_truncation (`float`, *optional*, defaults to 1.0):
diff --git a/src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py b/src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py
index 132c22c0cff3..7ab2febffd48 100644
--- a/src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py
+++ b/src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py
@@ -597,10 +597,9 @@ def __call__(
                 will be used.
             guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). 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.
+                Z-Image uses the formula `pred = pos + guidance_scale * (pos - neg)`, so guidance scale is enabled
+                by setting `guidance_scale > 0`. Higher guidance scale encourages to generate images that are closely
+                linked to the text `prompt`, usually at the expense of lower image quality.
             cfg_normalization (`bool`, *optional*, defaults to False):
                 Whether to apply configuration normalization.
             cfg_truncation (`float`, *optional*, defaults to 1.0):
diff --git a/src/diffusers/pipelines/z_image/pipeline_z_image_omni.py b/src/diffusers/pipelines/z_image/pipeline_z_image_omni.py
index 50776ceaf34d..0409aea94386 100644
--- a/src/diffusers/pipelines/z_image/pipeline_z_image_omni.py
+++ b/src/diffusers/pipelines/z_image/pipeline_z_image_omni.py
@@ -410,10 +410,9 @@ def __call__(
                 will be used.
             guidance_scale (`float`, *optional*, defaults to 5.0):
                 Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). 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.
+                Z-Image uses the formula `pred = pos + guidance_scale * (pos - neg)`, so guidance scale is enabled
+                by setting `guidance_scale > 0`. Higher guidance scale encourages to generate images that are closely
+                linked to the text `prompt`, usually at the expense of lower image quality.
             cfg_normalization (`bool`, *optional*, defaults to False):
                 Whether to apply configuration normalization.
             cfg_truncation (`float`, *optional*, defaults to 1.0):