Skip to content

vllm_omni.model_extras.vace ¶

VACE_EXTRA_BODY_PARAMS `module-attribute` ¶

VACE_EXTRA_BODY_PARAMS: frozenset[str] = frozenset()

VACE_EXTRA_OUTPUT_PARAMS `module-attribute` ¶

VACE_EXTRA_OUTPUT_PARAMS: frozenset[str] = frozenset()

build_image_to_video_prompt ¶

build_image_to_video_prompt(
    prompt: str,
    negative_prompt: str | None,
    media_inputs: Mapping[str, Any],
    height: int | None = None,
    width: int | None = None,
    num_frames: int | None = None,
) -> dict[str, Any]

Build VACE's native video, mask, or reference-image conditioning.