mudler/LocalAI · error · ValueError

num_frames must not be negative

Error message

num_frames must not be negative

What it means

ValueError from longcat-video's generation RPC: num_frames is a proto int that must be >= 0. Zero means 'derive frame count automatically' (from audio duration or defaults); negative values are meaningless and rejected before dispatch to the base or avatar generation path.

Source

Thrown at backend/python/longcat-video/backend.py:273

        try:
            params, ignored_params = select_known_options(
                dict(request.params), REQUEST_PARAMS
            )
            if ignored_params:
                print(
                    f"longcat-video ignoring unknown request param(s): {', '.join(ignored_params)}",
                    file=sys.stderr,
                )

            os.makedirs(os.path.dirname(request.dst) or ".", mode=0o750, exist_ok=True)
            if hasattr(context, "add_callback"):
                context.add_callback(interrupt_if_cancelled)

            if request.start_image and not os.path.isfile(request.start_image):
                raise ValueError("start_image is not a readable staged file")
            if request.num_frames < 0:
                raise ValueError("num_frames must not be negative")

            if self.model_kind == MODEL_KIND_BASE:
                if request.audio:
                    raise ValueError(
                        "audio input requires a LongCat-Video-Avatar-1.5 model"
                    )
                self._generate_base(request, params)
            else:
                self._generate_avatar(request, params, context)

            return backend_pb2.Result(
                message="Video generated successfully", success=True
            )
        except ValueError as err:
            return self._fail(context, grpc.StatusCode.INVALID_ARGUMENT, str(err))
        except Exception as err:
            print(f"Error generating LongCat video: {err}", file=sys.stderr)
            traceback.print_exc()

View on GitHub (pinned to 44413a9d06)

Solutions

1. Send num_frames=0 to let the backend choose the frame count automatically
2. Clamp client-side computed frame counts to >= 0 before building the request

Example fix

# before
req.num_frames = requested_frames  # can be -1

# after
req.num_frames = max(0, requested_frames)

def sanitize_video_request(req):
    if req.num_frames < 0:
        req.num_frames = 0  # 0 = backend default/derived
    return req

try:
    stub.GenerateVideo(req)
except grpc.RpcError as e:
    if "num_frames" in (e.details() or ""):
        req.num_frames = 0
        stub.GenerateVideo(req)
    else:
        raise

When it happens

Trigger: Sending VideoRequest with num_frames=-1 intending 'unlimited' or 'auto' (the correct auto value is 0); computing num_frames from user input that can go negative (e.g. duration*fps - offset).

Common situations: Client arithmetic produces a negative count; users coming from APIs where -1 means 'default'.

Related errors

• resolution must be 480p or 720p
• start_image is not a readable staged file
• audio input requires a LongCat-Video-Avatar-1.5 model
• audio is required for LongCat-Video-Avatar-1.5
• dataset_source is required (path to a preprocessed dataset)

AI-assisted analysis of mudler/LocalAI@44413a9d06 (2026-08-15). Data as JSON: /api/errors/f3617fd11331d5dc. Report an issue: GitHub.