Nodes/Runware.ai ComfyUI Inference API Integration/BytePlus Video Enhancement Standard
ComfyUI Node

BytePlus Video Enhancement Standard

BytePlus video enhancement with a style dial for the source

By Runware·Created 2 years ago·Updated about a month ago· 140
BytePlus Video Enhancement Standard
    • image
    video
    resolution(default)
    fpsfalse
    fps_value15.00
    settings.bitratemedium
    settings.resolutionLimitfalse
    settings.resolutionLimit_value128
    settings.stylecommon
    ttlfalse
    ttl_value60
    outputFormatMP4
    outputQuality95

    This is the sibling of the BytePlus Video Enhancement Pro node, with one extra control that makes it the more interesting of the two for anyone cleaning up real footage: a style preset that tells the enhancer what kind of clip this is. Same cloud upscaling job, same one-input API, but instead of a generic "make it better," you can say "this is old film" or "this is a short-form vertical video" and get enhancement tuned for it.

    Both nodes share the same core - feed a video, get an enhanced version back. The Standard tier is the one to reach for when your source has a character, not just low resolution.

    The inputs that matter

    • video (required, STRING): the source clip as a UUID or URL.
    • settings.style - the dial that makes this node worth picking over Pro:
      • common - the generic default.
      • ugc - user-generated content: phone and webcam footage.
      • short_series - short-form/vertical video, where the enhancement treats the clip like a social asset.
      • aigc - AI-generated video, which is a genuinely useful admission that the source is already synthetic and needs cleanup rather than realism.
      • old_film - archival footage: the enhancer knows to fight grain and instability instead of inventing detail.
    • resolution: 240p4k presets, defaulting to the input's size and aspect.
    • settings.bitrate (low/medium/high) and the gated fps and settings.resolutionLimit toggles: same as Pro.
    • outputFormat (MP4/WEBM/MOV) and outputQuality (default 95).

    And the same quirk as its sibling, so it bears repeating: the output is typed IMAGE, not VIDEO. The widgets all describe a video, but Runware's catalog types these enhancement nodes with an image output - wire it into an image preview/save node and don't hunt for a VIDEO socket that isn't there.

    How it works

    Identical pack machinery to Pro: the clip goes up, BytePlus runs on Runware's cloud, the enhanced file comes back and is converted into your graph. The style value just rides along in the request and tells the enhancer which recipe to use. Cost per run shows on the title bar.

    Install and gotchas

    One-time pack install - ComfyUI Manager, search Runware, or git clone https://github.com/Runware/ComfyUI-Runware into custom_nodes + pip install -r requirements.txt - then restart and add a Runware API key (Settings → Runware API key, RUNWARE_API_KEY, or runware auth login).

    The three things to remember: mind the IMAGE-typed output, use the style preset (it's the entire reason Standard exists over Pro), and treat 4K + high bitrate as a real bill line. If your clip is honest 480p phone footage, ugc will do more for it than any resolution knob.

    CategoryRunware/Image/bytedance

    Inputs (12)

    NameTypeDefaultDescription
    videoSTRINGVideo input (UUID or URL).
    resolutionoptCOMBO(default)Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.
    fpsoptBOOLEANfalseEnable to set fps. Off uses the model's default.
    fps_valueoptFLOAT15.0015–120Frames per second for video generation. Higher values create smoother motion but require more processing time.
    settings.bitrateoptCOMBOmediumControls the output average bitrate, affecting quality and file size.
    settings.resolutionLimitoptBOOLEANfalseEnable to set settings.resolutionLimit. Off uses the model's default.
    settings.resolutionLimit_valueoptINT128128–2160Pixel limit for the short side of the target resolution. Scales proportionally, maintaining aspect ratio.
    settings.styleoptCOMBOcommonVideo enhancement scenario preset.
    ttloptBOOLEANfalseEnable to set ttl. Off uses the model's default.
    ttl_valueoptINT60Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.
    outputFormatoptCOMBOMP4File format for the generated video.
    outputQualityoptINT9520–99Compression quality of the output. Higher values preserve quality but increase file size.

    Outputs (1)

    NameTypeDescription
    imageIMAGE