ComfyUI Node

PixVerse V3.5

The workhorse text-to-video, effects included

By Runware·Created 2 years ago·Updated about a month ago· 140
PixVerse V3.5
  • frameImages
  • video
positivePrompt
negativePrompt
size720p (16:9)
seed0
duration(default)
numberResults1
providerSettings.pixverse.effect(default)
providerSettings.pixverse.motionModenormal
safetyfalse
safety.checkContentfalse
safety.modefast
providerSettings.pixverse.style(default)
ttlfalse
ttl_value60
outputFormatMP4
outputQuality95

PixVerse V3.5 is the middle child of the PixVerse text-to-video line in the Runware pack, and for a lot of people it's the one that's good enough. You type a prompt, optionally give it a starting frame, and a few seconds of motion comes back as a native VIDEO. It's the V3.5 node's party trick that keeps it relevant next to the newer versions: a built-in library of effect templates - the viral "skeleton dance," "kiss me AI," "subject 3 fever" moves that flooded short-form video - that you can apply with one dropdown instead of reverse-engineering in the prompt.

PixVerse is a consumer AI video service that got big on exactly these effects, and Runware exposes it per-model as a node. The KB's video framing is worth keeping in mind: closed video models still hold the edge on polish and native audio, and this is you renting that edge by the run instead of buying a subscription.

What you actually set

  • positivePrompt - required. Describe the scene and the motion; "slow zoom on a lighthouse at dusk, waves crashing" is the shape of a good one.
  • frameImages - IMAGE socket for image-to-video. Feed it a frame you generated and PixVerse animates from there.
  • negativePrompt - what to keep out.
  • size - resolution presets from 360p to 1080p, in 16:9, 4:3, 1:1, 3:4, 9:16, or "from input" flavors. Default is 720p (16:9).
  • duration - 5 or 8 seconds (default is the model default). 8 seconds costs more; 5 is the standard clip.
  • providerSettings.pixverse.style - anime, 3d_animation, clay, comic, cyberpunk, or default. One dropdown, instant restyle.
  • providerSettings.pixverse.effect - the viral movement templates. This is the reason to pick V3.5 specifically.
  • providerSettings.pixverse.motionMode - normal or fast. Fast is snappier, less refined.
  • seed and numberResults - reproducibility and up to N takes.

Output: one video socket, type VIDEO.

Install

One-time, pack-wide: 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. Light dependencies (runware-sdk, pillow, soundfile), no weights on disk.

Where people get burned

  • safety.mode defaults to none. Content checking is off by default on the PixVerse video nodes; fast and full exist if you want it.
  • Effects are the point, and they're gimmicky. The template names are meme-tier on purpose. If you want earnest cinematic motion, set effect to default and lean on the prompt.
  • 8-second runs cost more. Duration is a real price lever; watch the title-bar cost before queuing a batch.

The takeaway: V3.5 is the budget-adjacent choice that's surprisingly capable - good enough motion, plus the effects nobody else has. If you want sharper camera work, step up to V4.

CategoryRunware/Video/pixverse

Inputs (17)

NameTypeDefaultDescription
positivePromptSTRINGText prompt describing elements to include in the generated output.
frameImagesoptIMAGE
negativePromptoptSTRINGPrompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).
sizeoptCOMBO720p (16:9)Output size. Only one of resolution or dimensions is sent.
seedoptINT00–2147483647Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.
durationoptCOMBO(default)Length 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.pixverse.effectoptCOMBO(default)Visual effect template.
providerSettings.pixverse.motionModeoptCOMBOnormalMotion intensity in the generated 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.
providerSettings.pixverse.styleoptCOMBO(default)Artistic style aesthetic 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