Add documentation and improve test stability for ZImageInpaintPipeline

- Add torch.empty fix for x_pad_token and cap_pad_token in test
- Add # Copied from annotations for encode_prompt methods
- Add documentation with usage example and autodoc directive

Author: CalamitousFelicitousness

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

@@ -53,6 +53,41 @@ image = pipe(
 image.save("zimage_img2img.png")
 ```
 
+## Inpainting
+
+Use [`ZImageInpaintPipeline`] to inpaint specific regions of an image based on a text prompt and mask.
+
+```python
+import torch
+import numpy as np
+from PIL import Image
+from diffusers import ZImageInpaintPipeline
+from diffusers.utils import load_image
+
+pipe = ZImageInpaintPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+init_image = load_image(url).resize((1024, 1024))
+
+# Create a mask (white = inpaint, black = preserve)
+mask = np.zeros((1024, 1024), dtype=np.uint8)
+mask[256:768, 256:768] = 255  # Inpaint center region
+mask_image = Image.fromarray(mask)
+
+prompt = "A beautiful lake with mountains in the background"
+image = pipe(
+    prompt,
+    image=init_image,
+    mask_image=mask_image,
+    strength=1.0,
+    num_inference_steps=9,
+    guidance_scale=0.0,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+image.save("zimage_inpaint.png")
+```
+
 ## ZImagePipeline
 
 [[autodoc]] ZImagePipeline
@@ -64,3 +99,9 @@ image.save("zimage_img2img.png")
 [[autodoc]] ZImageImg2ImgPipeline
 	- all
 	- __call__
+
+## ZImageInpaintPipeline
+
+[[autodoc]] ZImageInpaintPipeline
+	- all
+	- __call__

src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py

@@ -204,6 +204,7 @@ def __init__(
             do_convert_grayscale=True,
         )
 
+    # Copied from diffusers.pipelines.z_image.pipeline_z_image.ZImagePipeline.encode_prompt
     def encode_prompt(
         self,
         prompt: Union[str, List[str]],
@@ -238,6 +239,7 @@ def encode_prompt(
             negative_prompt_embeds = []
         return prompt_embeds, negative_prompt_embeds
 
+    # Copied from diffusers.pipelines.z_image.pipeline_z_image.ZImagePipeline._encode_prompt
     def _encode_prompt(
         self,
         prompt: Union[str, List[str]],

tests/pipelines/z_image/test_z_image_inpaint.py

@@ -109,6 +109,12 @@ def get_dummy_components(self):
             axes_dims=[8, 4, 4],
             axes_lens=[256, 32, 32],
         )
+        # `x_pad_token` and `cap_pad_token` are initialized with `torch.empty`.
+        # This can cause NaN data values in our testing environment. Fixating them
+        # helps prevent that issue.
+        with torch.no_grad():
+            transformer.x_pad_token.copy_(torch.ones_like(transformer.x_pad_token.data))
+            transformer.cap_pad_token.copy_(torch.ones_like(transformer.cap_pad_token.data))
 
         torch.manual_seed(0)
         vae = AutoencoderKL(