[Model] Add LingBot-World I2V support

[pakkah]

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

Purpose

Add LingbotWorldPipeline support for robbyant/lingbot-world-base-cam and integrate it into the existing image-to-video example flow. This PR closes #1045.

Implementation notes:

• Follow the DreamID-Omni integration pattern: keep the pipeline self-loading, reuse an external dependency repo via a download helper, and keep the vllm-omni-specific model adaptation local
• Support LingBot-World control signals through the offline serving --action-path arg, which matches the upstream LingBot-World usage pattern
• The API form for model-specific control signals is still to be determined [RFC]: World Model Support #1987 , so we leave that to a follow-up PR. In this PR, online serving remains limited to plain I2V without control signals.

Test Plan

cd examples/offline_inference/image_to_video

python download_lingbot_world.py \
  --model-id robbyant/lingbot-world-base-cam \
  --output-dir ./lingbot-world-base-cam

PROMPT="$(cat /tmp/vllm-omni-dependency/lingbot-world/examples/00/prompt.txt)"

python image_to_video.py \
  --model ./lingbot-world-base-cam \
  --image /tmp/vllm-omni-dependency/lingbot-world/examples/00/image.jpg \
  --action-path /tmp/vllm-omni-dependency/lingbot-world/examples/00 \
  --prompt "$PROMPT" \
  --height 480 \
  --width 832 \
  --num-frames 161 \
  --guidance-scale 5.0 \
  --guidance-scale-high 5.0 \
  --num-inference-steps 20 \
  --flow-shift 10.0 \
  --fps 16 \
  --output lingbot_world_base_cam_examples00.mp4

python image_to_video.py \
  --model ./lingbot-world-base-cam \
  --image /tmp/vllm-omni-dependency/lingbot-world/examples/00/image.jpg \
  --prompt "$PROMPT" \
  --height 480 \
  --width 832 \
  --num-frames 161 \
  --guidance-scale 5.0 \
  --guidance-scale-high 5.0 \
  --num-inference-steps 20 \
  --flow-shift 10.0 \
  --fps 16 \
  --output lingbot_world_base_cam_no_control.mp4

Test Result

---

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)