PixVerse V5 Fast
Iterate like you mean it
- frameImages
- video
PixVerse V5 Fast is the iteration node: the stripped-down, cheaper, quicker version of the V5 family, built for the part of video work nobody talks about - the first five drafts that are all wrong. You type a prompt, get a video back fast, decide it's not it, change a word, go again. That loop is brutal on a premium per-run model and fine on V5 Fast, which trades away the bells and whistles (no style presets, no effect templates, no thinking mode) for speed and a smaller bill.
The shape is familiar PixVerse: prompt in, optional starting frame, VIDEO out. What's missing from the dropdowns tells you what this node is for - it's not for hero shots or stylized loops, it's for finding the motion, the timing, the framing that works, so that when you're ready to commit, you spend the real money on the full V5.
What you actually set
positivePrompt- required. Keep it descriptive but don't over-scope; you're testing a concept.frameImages-IMAGEsocket for image-to-video.size- resolution presets from 360p to 1080p, default720p (16:9).duration- 5 or 8 seconds.negativePrompt,seed,numberResults- the usuals.
That's genuinely about it. No style, no effect, no camera controls. Output is 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. Light dependencies, no model downloads.
Where people get burned
- "Fast" is relative, not absolute. It's cheaper and quicker than full V5, but it's still a cloud video generation - a handful of seconds of render plus queue time. Don't expect instant.
- Quality is visibly a notch down. That's the trade you're making on purpose. If you find yourself taking V5 Fast outputs to production, you're using the wrong node.
safety.modedefaults tonone. Same opt-in story as the other video nodes in the pack.
The honest take: V5 Fast is the node you reach for when you're doing the work - testing, iterating, blocking out a sequence - and V5 is the node you reach for when you're done thinking. Most video workflows need both; this one is the one that keeps your balance from bleeding out on drafts.
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| positivePrompt | STRING | Text prompt describing elements to include in the generated output. | |
| frameImagesopt | IMAGE | — | |
| negativePromptopt | STRING | Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1). | |
| sizeopt | COMBO | 720p (16:9) | Output size. Only one of resolution or dimensions is sent. |
| seedopt | INT | 00–2147483647 | Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. |
| durationopt | COMBO | (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). |
| numberResultsopt | INT | 11–4 | Number of results to generate. Each result uses a different seed, producing variations of the same parameters. |
| safetyopt | BOOLEAN | false | Enable to set safety. Off uses the model's default. |
| safety.checkContentopt | BOOLEAN | false | Enable or disable content safety checking. |
| safety.modeopt | COMBO | fast | Safety checking mode for video generation. |
| ttlopt | BOOLEAN | false | Enable to set ttl. Off uses the model's default. |
| ttl_valueopt | INT | 60 | Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. |
| outputFormatopt | COMBO | MP4 | File format for the generated video. |
| outputQualityopt | INT | 9520–99 | Compression quality of the output. Higher values preserve quality but increase file size. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |