Fix: Normalize batch inputs to 5D tensors for Qwen-Image-Edit

[akshan-main]

What does this PR do?

Enables batch inference for QwenImageEditPlusPipeline by normalizing input tensor shapes and handling variable-length prompt embeddings.

Description

Addresses issue #12458.

I identified two blockers preventing batch inference in the current pipeline:

1. 5D Tensor Requirement: The underlying Qwen2-VL model treats inputs as video (B, C, F, H, W). The pipeline was passing 4D tensors (B, C, H, W), causing immediate shape mismatches.

   • Fix: Added a pre-processing step to explicitly unsqueeze the frame dimension for static images when batch_size > 1.

2. Tokenizer Batching Issues: The Qwen2VLProcessor produces variable-length embeddings for different prompts, which caused RuntimeError or IndexError when trying to batch encode them directly.

   • Fix: Refactored encode_prompt to process prompts individually in a loop, then pad the resulting embeddings to the maximum sequence length in the batch before concatenating.

This ensures robust batching for both images and prompts. I also added checks to handle the tuple vs list input ambiguity reported in the original issue.

Note on Batching Logic

To resolve the ambiguity between "Multi-Image Conditioning" and "Batch Inference", I implemented the following routing logic in encode_prompt:

1. Single String Prompt (prompt="string"):

   • Behavior: Joint Condition. The pipeline treats all provided images as a single context for one generation task.
   • Use Case: Style transfer or merging elements from multiple reference images.

2. List of Prompts (prompt=["s1", "s2"]):

   • Behavior: Parallel Batch. The pipeline maps images to prompts 1-to-1.
   • Use Case: Processing a dataset (e.g., editing 50 different images with 50 different instructions at once (given hardware allows for it)).

This ensures robust batching for both images and prompts. I also added checks to handle the tuple vs list input ambiguity reported in the original issue.

Fixes #12458

Before submitting

• This PR fixes a typo or improves the docs.
• Did you read the contributor guideline?
• Did you read our philosophy doc?
• Was this discussed/approved via a GitHub issue? (Issue [Qwen-image-edit] Batch Inference Issue / Feature Request #12458)
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? (Verified via reproduction script)

Who can review?

@yiyixuxu @sayakpaul @DN6