PixVerse V5.5
The version where PixVerse got audio and 'thinking'
- frameImages
- video
PixVerse V5.5 sits in a slightly awkward spot in the lineage: V4.5 had the viral effect templates, V6 is the current flagship, and V5.5 is the transitional version that got the two features the later models kept - audio generation and an "enhanced reasoning" mode. It's not the newest PixVerse and it knows it, but it's the cheap, proven middle option when you want the audio-and-style feature set without paying V6's premium.
The honest pitch: if your use case is "prompt → decent video clip, possibly with sound, in a standard aspect ratio," V5.5 is the value pick. It runs the same positivePrompt-driven flow as every other PixVerse node, returns a native VIDEO, and the differences from V6 are mostly depth of features, not a night-and-day quality gap. For batch work and drafts, that's a real advantage.
Inputs that matter
positivePrompt required. The knobs worth knowing:
providerSettings.pixverse.audio- the audio toggle, matching V6'ssettings.audio. On, and the clip gets a generated soundtrack. Off (default) for silent drafts, because audio costs more.providerSettings.pixverse.thinking-auto,enabled, ordisabled. This is the "enhanced reasoning" mode: the model thinks harder about the prompt before generating.autois the sane default;enabledbuys better prompt comprehension for complex scenes at more latency,disabledtrades comprehension for speed.providerSettings.pixverse.multiClip- multi-shot generation with varying camera angles. This is the cinematic feature, same as V6's.providerSettings.pixverse.style-anime,3d_animation,clay,comic,cyberpunk, or default.duration- an enable-toggle plusduration_value(seconds) - a different pattern from V6's direct slider, but same idea.frameImages- first-frame image-to-video.size- the resolution/aspect dropdown from 360p to 1080p, including "from input" variants.
negativePrompt, seed, numberResults (up to 4), outputFormat (MP4/WEBM/MOV), outputQuality, and safety round out the standard set. No camera-movement or effect-template dropdowns here - that was V4.5's party trick.
How it works
The node sends pixverse:1@6 as a videoInference task through the Runware SDK. The result comes back as a native VIDEO socket for SaveVideo or whatever eats a VIDEO. Cloud-only, pay-per-run, cost on the title bar.
Install and gotchas
cd ComfyUI/custom_nodes
git clone https://github.com/Runware/ComfyUI-Runware
pip install -r ComfyUI-Runware/requirements.txt
Restart; API key via Settings → "Runware API key", RUNWARE_API_KEY, or runware auth login. Paid, minimum top-up.
The trap is version confusion: people pick up this node because it's "PixVerse" and then expect V6 features or the V4.5 template list, neither of which it has. Check the version you actually want before you queue. And thinking: enabled is a real cost/latency multiplier - it's the kind of toggle that quietly doubles your bill if you leave it on for every run. Use it for the complex prompts, leave it on auto otherwise. If you need the effect templates, go grab the V4.5 node; if you need the newest quality, V6 - this one's the reliable middle child.
Inputs (19)
| 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 | BOOLEAN | false | Enable to set duration. Off uses the model's default. |
| duration_valueopt | FLOAT | 0.00 | 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. |
| providerSettings.pixverse.audioopt | BOOLEAN | false | Enable audio generation. |
| providerSettings.pixverse.multiClipopt | BOOLEAN | false | Enable multi-shot generation with varying camera angles. |
| 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. |
| providerSettings.pixverse.styleopt | COMBO | (default) | Artistic style aesthetic for video generation. |
| providerSettings.pixverse.thinkingopt | COMBO | auto | Enhanced reasoning mode. |
| 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 | — |