calesthio/OpenMontage · error · ValueError

Kling identify-face response contained no faces

Error message

Kling identify-face response contained no faces

What it means

ValueError from _identify_faces when the response parsed cleanly (session_id present, face list is a list) but the list is empty. Kling analyzed the video and found zero human faces, so there is nothing to lip-sync. This is a content problem: the video does not contain a detectable face.

Source

Thrown at tools/avatar/kling_lip_sync.py:275

    def _identify_faces(self, client: KlingClient, inputs: dict[str, Any]) -> dict[str, Any]:
        request = self._build_identify_request(inputs)
        data = client.post(request["path"], request["payload"])
        payload = data.get("data") or {}
        session_id = payload.get("session_id")
        if not session_id:
            raise ValueError(f"Kling identify-face response missing data.session_id: {data}")
        faces = (
            payload.get("face_data")
            or payload.get("faces")
            or payload.get("face_list")
            or payload.get("face_infos")
            or payload.get("faces_info")
            or []
        )
        if not isinstance(faces, list):
            raise ValueError("Kling identify-face response face list is not a list")
        if not faces:
            raise ValueError("Kling identify-face response contained no faces")
        return {
            "session_id": str(session_id),
            "faces": faces,
            "raw_response": data,
            "request": request,
        }

    def _identify_result(self, inputs: dict[str, Any], identify: dict[str, Any], start: float) -> ToolResult:
        artifact_path = self._write_faces_artifact(inputs, identify)
        return ToolResult(
            success=True,
            data={
                "provider": self.provider,
                "model": "kling-official-lip-sync",
                "operation": "identify_face",
                "session_id": identify["session_id"],
                "faces": identify["faces"],
                "face_count": len(identify["faces"]),

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Confirm you passed the intended video (video_url/video_id) — check for a mix-up with b-roll.
2. Use a clip with a clearly visible, front-facing, reasonably sized human face.
3. Re-upload at higher resolution if the source was heavily compressed or small.
4. For animated characters, use a different pipeline — face identification is tuned for real humans.

try:
    identify = tool._identify_faces(client, inputs)
except ValueError as e:
    if "contained no faces" in str(e):
        # content issue: swap in a clip with a clearly visible human face
        raise

When it happens

Trigger: Running identify_face on a video with no people (landscape, screen recording, text-only frames); a face too small/obscured/back-lit for the detector; an animated/illustrated character the detector does not recognize.

Common situations: Wrong video passed (b-roll instead of the talking-head clip); low-resolution uploads; side profiles or heavy occlusion; cartoon avatars.

Related errors

• Cannot select face without face_id/id: {face}
• Unsupported Kling lip-sync operation: {operation}
• Kling identify-face response missing data.session_id: {data}
• Kling identify-face response face list is not a list
• Kling identify_face requires video_url or video_id; local vi

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/96e5fe0d0bfaa357. Report an issue: GitHub.