What does this PR do?

Fixes #14042

Description and Motivation

The diffusers library currently provides a dedicated Flux2KleinPipeline for text-to-image generation, but lacks a native Image-to-Image (Img2Img) pipeline for the FLUX.2 Klein architecture.

This PR introduces a dedicated Flux2KleinImg2ImgPipeline by adapting the existing Diffusers img2img workflow to the FLUX.2 Klein architecture, carefully preserving its specific latent processing and normalization behavior.

Implementation Details

• Standard Img2Img Workflow: Reuses the standard Diffusers workflow, including proper image preprocessing, VAE encoding, timestep slicing based on strength, latent noise initialization, and denoising via FlowMatchEulerDiscreteScheduler (using scale_noise).
• Klein Architecture Alignment: Integrates seamlessly with Klein's specific _encode_vae_image path, preserving crucial patchification and batch-normalization behavior.
• Safety & Hardware Optimizations: Maintains existing Klein image area safeguards (capping at 1024x1024) to avoid excessive memory usage.
• Input Validation: Adds robust defensive checks, including strength boundary validation (0, 1] and batch-size divisibility checking before tensor duplication.

Testing

• Verified import and pipeline registration through the Diffusers lazy-loading system.
• • Verified local end-to-end tensor flow, latent preparation, sequence length calculation, and dimension packing/unpacking using CPU mock implementations of the Klein Transformer and VAE.

(Note for Reviewers: I am opening this as a Draft PR to get feedback on the overall approach and architecture. Once the implementation direction is approved, I will add the standard fast/slow pipeline tests, import tests, and API documentation updates!)

Before submitting

• Did you use an AI agent (Claude Code, Codex, Cursor, etc.) to help with this PR? If so:
  • Did you read the Coding with AI agents guide?
  • Did you self-review the diff against .ai/review-rules.md?
• 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?
• Are you the author (or part of the team) of the model/pipeline (only applicable for model/pipeline related PRs)?

Who can review?

@yiyixuxu @sayakpaul