ComfyUI Node

Kling VIDEO O1 Standard

The cheap lane for learning what O1 edits can do

By Runware·Created 2 years ago·Updated about a month ago· 140
Kling VIDEO O1 Standard
  • referenceImages
  • frameImages
  • referenceVideos
  • video
positivePrompt
video
size960p (1:1)
duration5
numberResults1
providerSettings.klingai.keepOriginalSoundfalse
safetyfalse
safety.checkContentfalse
safety.modefast
ttlfalse
ttl_value60
outputFormatMP4
outputQuality95

Kling O1 Standard is the "prove it works" tier of Kling's edit-focused O1 line. It gives you the same source-video-rewriting behavior as O1 Pro at a lower price, which makes it the node you reach for while you're still learning what prompts O1 actually responds to. Once you've found something worth shipping, that's when Pro gets involved.

It's a closed model rendered on Runware's servers through the ComfyUI-Runware pack. Your hardware contributes nothing but the workflow. The node is the same thin glue as every other model in the pack: widgets become a request with model AIR klingai:kling@o1-standard and a videoInference task, the runware-sdk sends it over REST, and the returned MP4 comes back as a native VIDEO output you can wire into Preview Video or Save Video.

The inputs that matter

  • video - source clip as a URL or UUID; dimensions and duration follow the input. The heart of the O1 line.
  • positivePrompt - the edit instruction.
  • referenceImages, frameImages, referenceVideos - conditioning sockets for extra control.
  • width / height - pixel widgets at 1024 default for text-only runs.
  • duration + duration_value - gated off by default (the model has duration usage rules); enable to force 3–15 seconds.
  • keepOriginalSound - preserve the source clip's audio.
  • numberResults - 1–4 variations per queue.

No negative prompt, no size dropdown, no advanced_json - the control surface is intentionally small. Everything else (safety, ttl, outputFormat MP4, outputQuality 95) is fine at default.

The output

One video socket, type VIDEO, into a preview or save node. On an older ComfyUI build it falls back to a file path string - the fix is upgrading ComfyUI, not the pack.

Installing it

Same one-time pack install as everything else:

cd ComfyUI/custom_nodes
git clone https://github.com/Runware/ComfyUI-Runware
pip install -r ComfyUI-Runware/requirements.txt

Restart, set your key in ComfyUI Settings → Runware API key (or RUNWARE_API_KEY, or runware auth login), and queue. Dependencies are just the SDK, pillow, and soundfile.

Where people get burned

The recurring pack trap applies: video takes a URL or UUID, not a local path. The other one is expectations - Standard is the iteration tier, and judging O1 by its cheap renders is how people write the model off. Run Standard until the prompt behaves, then re-queue the winner on Pro. If the run info line shows a cost that surprises you, check numberResults before you assume the pricing changed.

CategoryRunware/Video/klingai

Inputs (16)

NameTypeDefaultDescription
positivePromptSTRINGText prompt describing elements to include in the generated output.
referenceImagesoptIMAGE
frameImagesoptIMAGE
referenceVideosoptRUNWARE_REFERENCEVIDEOS
videooptSTRINGVideo input (UUID or URL). Source video for prompt-based editing. Dimensions and duration match the input video.
sizeoptCOMBO960p (1:1)Output size. Only one of resolution or dimensions is sent.
durationoptINT5Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).
numberResultsoptINT11–4Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
providerSettings.klingai.keepOriginalSoundoptBOOLEANfalseMaintain the original sound from the reference video.
safetyoptBOOLEANfalseEnable to set safety. Off uses the model's default.
safety.checkContentoptBOOLEANfalseEnable or disable content safety checking.
safety.modeoptCOMBOfastSafety checking mode for video generation.
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
videoVIDEO