ComfyUI Node

P-Video-Animate

Bring a reference to life

By Runware·Created 2 years ago·Updated about a month ago· 140
P-Video-Animate
  • referenceImages
  • referenceVideos
  • video
positivePrompt
resolution720p
seed0
fps(default)
numberResults1
settings.preserveAudiotrue
safetyfalse
safety.checkContentfalse
safety.modefast
ttlfalse
ttl_value60
outputFormatMP4
outputQuality95

P-Video-Animate is the node for when you have an image of something and want it to move - really move, not just drift. Its required inputs tell the story: referenceImages and referenceVideos, because this model animates a subject with reference guidance from both a still and a motion source. Character animation, product shots that come alive, a character whose look is locked but whose motion comes from a second clip - that's the territory. It runs on Runware's cloud and returns a native VIDEO.

The pairing of image + video reference is what separates this from a plain image-to-video node. One reference gives the model the subject's look; the other gives it the motion to copy. That's why you'd reach for it over, say, P-Video with a single frame image.

What you actually set

  • referenceImages - required, IMAGE socket. The subject - the character, product, or scene you're animating.
  • referenceVideos - required, RUNWARE_REFERENCEVIDEOS builder socket. The motion source. Wire in a clip whose movement you want applied to the reference image.
  • positivePrompt - optional. Use it to steer the action when the reference video isn't the whole story.
  • resolution - 720p or 1080p (default 720p); matches input aspect ratio automatically.
  • fps - model default, 24, or 48.
  • settings.preserveAudio - default True: keep the source video's audio track in the output. If your reference clip has sound you want to carry over, this is the switch; turn it off for silent output.
  • seed, numberResults - the usuals.

Output: one video socket, type VIDEO.

Install

One-time pack install: ComfyUI Manager → search Runware → install → restart, or

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

API key into ComfyUI Settings → Runware API key or RUNWARE_API_KEY. Nothing heavy installs; the model is cloud-side.

Where people get burned

  • The reference video drives everything. A jumpy, noisy reference clip produces jumpy, noisy animation. Your motion quality is capped by the clip you feed it.
  • Both references have to be reachable. referenceVideos is a builder socket feeding the cloud - a local file path won't cut it; the clip needs to be uploadable/URL-reachable.
  • safety.mode defaults to none. Opt into fast/full if you want a guardrail.
  • It's a premium video run. Two references plus motion means a meatier request and a bigger per-run cost. Check the title bar before batching.

The verdict: if your workflow is "this exact character, doing this exact motion," nothing else in the pack does it as directly. If you just want prompt-to-video, the simpler P-Video node is cheaper and faster.

CategoryRunware/Video/prunaai

Inputs (15)

NameTypeDefaultDescription
referenceImagesIMAGE
referenceVideosRUNWARE_REFERENCEVIDEOS
positivePromptoptSTRINGText prompt describing elements to include in the generated output.
resolutionoptCOMBO720pResolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.
seedoptINT00–2147483647Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.
fpsoptCOMBO(default)Frames per second for video generation. Higher values create smoother motion but require more processing time.
numberResultsoptINT11–4Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
settings.preserveAudiooptBOOLEANtruePreserve the source video audio track in the output.
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