Feature/zimage inpaint pipeline

[CalamitousFelicitousness]

What does this PR do?

This PR adds an inpainting pipeline for Z-Image. The summary of changes are below:

• Implemented the ZImageInpaintPipeline class for mask-based inpainting
• Updated the pipeline structure to include ZImageInpaintPipeline alongside ZImagePipeline and ZImageImg2ImgPipeline
• Mapped the new ZImageInpaintPipeline in AUTO_INPAINT_PIPELINES_MAPPING
• Added unit tests for ZImageInpaintPipeline with torch.empty fix for test stability
• Updated dummy objects to include ZImageInpaintPipeline
• Added documentation with usage example

Closes issue #12752

Tested using a simple script:

Testing script

  #!/usr/bin/env python
  """Test script for ZImage inpaint support."""

  import sys
  sys.path.insert(0, '/home/ohiom/diffusers/src')

  import torch
  import numpy as np
  from PIL import Image
  from diffusers import ZImageInpaintPipeline

  # Paths
  MODEL_PATH =
  "database/models/huggingface/models--Tongyi-MAI--Z-Image-Turbo/snapshots/78771b7e11b922c868dd766476bda1f4fc6bfc96"
  INPUT_IMAGE_PATH = "death_remix_1024.png"

  print("Loading ZImageInpaintPipeline...")
  pipe = ZImageInpaintPipeline.from_pretrained(
      MODEL_PATH,
      torch_dtype=torch.bfloat16,
      local_files_only=True,
  )
  pipe.to("cuda")
  print("Pipeline loaded.")

  # Load input image
  print(f"\nLoading input image from {INPUT_IMAGE_PATH}...")
  input_image = Image.open(INPUT_IMAGE_PATH).convert("RGB")
  print(f"Input image size: {input_image.size}")

  # Create a mask (white = inpaint, black = preserve)
  width, height = input_image.size
  mask = np.zeros((height, width), dtype=np.uint8)
  h_start, h_end = height // 4, 3 * height // 4
  w_start, w_end = width // 4, 3 * width // 4
  mask[h_start:h_end, w_start:w_end] = 255
  mask_image = Image.fromarray(mask)

  # Generate an inpainted image
  prompt = "a woman with pale skin in a black shirt, oil painting style"
  strength = 0.75

  print(f"\nGenerating inpainted image with prompt: {prompt}")
  print(f"Strength: {strength}")

  image = pipe(
      prompt=prompt,
      image=input_image,
      mask_image=mask_image,
      strength=strength,
      num_inference_steps=8,
      guidance_scale=1.0,
      generator=torch.Generator(device="cuda").manual_seed(42),
  ).images[0]

  output_path = "test_zimage_inpaint_output.png"
  image.save(output_path)
  print(f"\nImage saved to {output_path}")

LoRA functionality is also supported (inherited from ZImageLoraLoaderMixin).

Before submitting

• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@yiyixuxu @asomoza @sayakpaul

[Copilot]

Pull request overview

This PR adds a comprehensive inpainting pipeline for Z-Image, extending the existing Z-Image family of pipelines (text-to-image, img2img, controlnet) with mask-based inpainting capabilities. The implementation follows established patterns from other inpainting pipelines in the diffusers library while adapting to Z-Image's specific requirements (e.g., complex64 RoPE embeddings, flow matching scheduler).

Changes:

• Implemented ZImageInpaintPipeline with full inpainting support including mask blending and strength-based denoising control
• Added comprehensive test suite covering inference, batch processing, strength validation, mask functionality, VAE tiling, and device offloading
• Integrated the pipeline into auto_pipeline infrastructure with proper model mapping for "z-image" model type
• Updated all necessary init.py files and dummy objects for proper exports
• Added documentation with usage examples

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py	New inpainting pipeline implementation with prepare_mask_latents, prepare_latents, and main call method for mask-based image inpainting
tests/pipelines/z_image/test_z_image_inpaint.py	Comprehensive test suite including inference tests, strength parameter validation, mask functionality tests, and compatibility tests
src/diffusers/pipelines/z_image/init.py	Added ZImageInpaintPipeline to module exports
src/diffusers/pipelines/init.py	Added ZImageInpaintPipeline to main pipelines module exports
src/diffusers/init.py	Added ZImageInpaintPipeline to top-level diffusers exports
src/diffusers/pipelines/auto_pipeline.py	Mapped ZImageInpaintPipeline to "z-image" in AUTO_INPAINT_PIPELINES_MAPPING
src/diffusers/utils/dummy_torch_and_transformers_objects.py	Added dummy ZImageInpaintPipeline class for when dependencies are not available
docs/source/en/api/pipelines/z_image.md	Added inpainting section with usage example and API reference

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[CalamitousFelicitousness]

@yiyixuxu Ready for re-review.