Feature/zimage inpaint pipeline (#13006)

* Add ZImageInpaintPipeline

Updated the pipeline structure to include ZImageInpaintPipeline
    alongside ZImagePipeline and ZImageImg2ImgPipeline.
Implemented the ZImageInpaintPipeline class for inpainting
    tasks, including necessary methods for encoding prompts,
    preparing masked latents, and denoising.
Enhanced the auto_pipeline to map the new ZImageInpaintPipeline
    for inpainting generation tasks.
Added unit tests for ZImageInpaintPipeline to ensure
    functionality and performance.
Updated dummy objects to include ZImageInpaintPipeline for
    testing purposes.

* 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

* Address PR review feedback for ZImageInpaintPipeline

Add batch size validation and callback handling fixes per review,
using diffusers conventions rather than suggested code verbatim.

* Update src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py

Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>

* Update src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py

Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>

* Add input validation and fix XLA support for ZImageInpaintPipeline

- Add missing is_torch_xla_available import for TPU support
- Add xm.mark_step() in denoising loop for proper XLA execution
- Add check_inputs() method for comprehensive input validation
- Call check_inputs() at the start of __call__

Addresses PR review feedback from @asomoza.

* Cleanup

---------

Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>

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/__init__.py

@@ -696,6 +696,7 @@
             "ZImageControlNetInpaintPipeline",
             "ZImageControlNetPipeline",
             "ZImageImg2ImgPipeline",
+            "ZImageInpaintPipeline",
             "ZImageOmniPipeline",
             "ZImagePipeline",
         ]
@@ -1428,6 +1429,7 @@
             ZImageControlNetInpaintPipeline,
             ZImageControlNetPipeline,
             ZImageImg2ImgPipeline,
+            ZImageInpaintPipeline,
             ZImageOmniPipeline,
             ZImagePipeline,
         )

src/diffusers/pipelines/__init__.py

@@ -410,11 +410,12 @@
         "Kandinsky5I2IPipeline",
     ]
     _import_structure["z_image"] = [
-        "ZImageImg2ImgPipeline",
-        "ZImagePipeline",
-        "ZImageControlNetPipeline",
         "ZImageControlNetInpaintPipeline",
+        "ZImageControlNetPipeline",
+        "ZImageImg2ImgPipeline",
+        "ZImageInpaintPipeline",
         "ZImageOmniPipeline",
+        "ZImagePipeline",
     ]
     _import_structure["skyreels_v2"] = [
         "SkyReelsV2DiffusionForcingPipeline",
@@ -870,6 +871,7 @@
             ZImageControlNetInpaintPipeline,
             ZImageControlNetPipeline,
             ZImageImg2ImgPipeline,
+            ZImageInpaintPipeline,
             ZImageOmniPipeline,
             ZImagePipeline,
         )

src/diffusers/pipelines/auto_pipeline.py

@@ -127,6 +127,7 @@
     ZImageControlNetInpaintPipeline,
     ZImageControlNetPipeline,
     ZImageImg2ImgPipeline,
+    ZImageInpaintPipeline,
     ZImageOmniPipeline,
     ZImagePipeline,
 )
@@ -235,6 +236,7 @@
         ("stable-diffusion-pag", StableDiffusionPAGInpaintPipeline),
         ("qwenimage", QwenImageInpaintPipeline),
         ("qwenimage-edit", QwenImageEditInpaintPipeline),
+        ("z-image", ZImageInpaintPipeline),
     ]
 )
 

src/diffusers/pipelines/z_image/__init__.py

@@ -26,6 +26,7 @@
     _import_structure["pipeline_z_image_controlnet"] = ["ZImageControlNetPipeline"]
     _import_structure["pipeline_z_image_controlnet_inpaint"] = ["ZImageControlNetInpaintPipeline"]
     _import_structure["pipeline_z_image_img2img"] = ["ZImageImg2ImgPipeline"]
+    _import_structure["pipeline_z_image_inpaint"] = ["ZImageInpaintPipeline"]
     _import_structure["pipeline_z_image_omni"] = ["ZImageOmniPipeline"]
 
 
@@ -42,6 +43,7 @@
         from .pipeline_z_image_controlnet import ZImageControlNetPipeline
         from .pipeline_z_image_controlnet_inpaint import ZImageControlNetInpaintPipeline
         from .pipeline_z_image_img2img import ZImageImg2ImgPipeline
+        from .pipeline_z_image_inpaint import ZImageInpaintPipeline
         from .pipeline_z_image_omni import ZImageOmniPipeline
 else:
     import sys