[BugFix]: Fix bagel single-stage img2img fallback to text2img bug

[princepride]

PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTTOM) HAVE BEEN CONSIDERED.

Purpose

When there is no injected KV cache:

 image_input = (first_prompt.get("multi_modal_data") or {}).get("image")

However, the key stored in the prompt is "img2img" instead of "image", which results in image_input = None. Consequently, the image is completely ignored, and the process degrades into a pure text-to-image (text2img) generation.

Test Plan

python3 examples/offline_inference/bagel/end2end.py   --stage-configs-path vllm_omni/model_executor/stage_configs/bagel_single_stage.yaml --modality img2img   --image-path women.jpg   --prompts "Let the woman wear a blue dress"

Test Result

Before:

After:

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan. Please provide the test scripts & test commands. Please state the reasons if your codes don't require additional test scripts. For test file guidelines, please check the test style doc
• The test results. Please paste the results comparison before and after, or the e2e results.
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model. Please run mkdocs serve to sync the documentation editions to ./docs.
• (Optional) Release notes update. If your change is user-facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)