perf: use cached face detection in map-faces live mode

[laurigates]

Summary

Switch process_frame_v2() live path from get_many_faces() to get_faces_optimized() so map-faces live mode benefits from time-based detection caching, matching the simple-mode live path.

get_faces_optimized() returns cached results when called within the detection interval (~33ms), avoiding redundant face detection on consecutive frames. This was already used in the simple (non-map) live mode but the map-faces live branch was still calling get_many_faces() directly.

Files changed

• modules/processors/frame/face_swapper.py — 1 line: get_many_faces → get_faces_optimized in the live stream branch of process_frame_v2()

Inspired by #1617.

Test plan

• Run live webcam with map-faces mode enabled (multiple source faces mapped to targets)
• Verify face detection caching is active (reduced CPU/GPU usage for detection)
• Confirm face swapping still works correctly with cached detection results
• Test with single-face and multi-face scenarios

🤖 Generated with Claude Code

Summary by Sourcery

Enhancements:

• Route live map-faces processing through the optimized face detection function to reuse recent detection results and reduce redundant work.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Switches live map-faces processing in process_frame_v2() to use the cached face detection path so live mode benefits from time-based detection caching, aligning behavior with the simple live mode path.

Sequence diagram for cached face detection in live map-faces processing

sequenceDiagram
    actor User
    participant LiveStream as LiveStreamLoop
    participant FaceSwapper as process_frame_v2
    participant Detector as get_faces_optimized
    participant Cache as DetectionCache

    User ->> LiveStream: start_live_map_faces()
    loop For_each_frame
        LiveStream ->> FaceSwapper: process_frame_v2(frame)
        FaceSwapper ->> Detector: get_faces_optimized(processed_frame)
        Detector ->> Cache: lookup(processed_frame_timestamp)
        alt cache_hit
            Cache -->> Detector: cached_detected_faces
            Detector -->> FaceSwapper: detected_faces
        else cache_miss
            Detector ->> Detector: run_face_detection()
            Detector ->> Cache: store(results, timestamp)
            Detector -->> FaceSwapper: detected_faces
        end
        FaceSwapper ->> FaceSwapper: map_faces_and_swap(detected_faces)
        FaceSwapper -->> LiveStream: swapped_frame
    end
    LiveStream -->> User: display_swapped_video

Loading

Flow diagram for live path in process_frame_v2 using get_faces_optimized

flowchart TD
    A[start_process_frame_v2] --> B{mode}
    B -->|image_or_video| C[analyze_precomputed_faces]
    C --> Z[end_process_frame_v2]

    B -->|live_or_webcam| D[preprocess_frame]
    D --> E[get_faces_optimized with processed_frame]
    E --> F{detected_faces_present}

    F -->|no| Z

    F -->|yes and many_faces_flag| G[default_source_face]
    G --> H[apply_face_swaps_to_all_detected_targets]
    H --> Z

    F -->|yes and not many_faces_flag| I[select_single_source_face]
    I --> J[apply_face_swap_to_primary_target]
    J --> Z[end_process_frame_v2]

Loading

File-Level Changes

Change	Details	Files
Use cached, time-optimized face detection for live/map-faces processing instead of uncached multi-face detection.	Replace get_many_faces() with get_faces_optimized() in the live stream branch of process_frame_v2() so live map-faces mode reuses recent detection results within the configured interval. Ensure that map-faces live behavior aligns with the existing simple live mode, reducing redundant detections and CPU/GPU usage while preserving face swapping behavior.	modules/processors/frame/face_swapper.py

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've reviewed your changes and they look great!

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}