Nodes/BizyAirPlus/Vidu Q3 Text To Video (Channel Edition)
ComfyUI Node

Vidu Q3 Text To Video (Channel Edition)

Vidu Q3 Turbo text-to-video, Channel edition — fastest and cheapest way into Q3

By siliconflow·Created 5 months ago·Updated about a month ago· 20
Vidu Q3 Text To Video (Channel Edition)
  • api_config
  • video
  • request_id
  • urls
prompt
resolution720P
duration5
aspect_ratio16:9
seed0
audiotrue
skip_errorfalse

If you want to know what Vidu Q3 is about and spend as little time and money as possible finding out, this is the node. Turbo text-to-video on the Channel route: no image prep, no frills, and - unlike its Pro Channel sibling - it comes with a seed and audio on by default. Cheap speed, and the schema shows it.

What this node does

BizyTRD_Vidu_Q3_Turbo_Base_T2V_API turns a prompt into a clip on the Turbo tier via the lean Channel edition. It's the T2V entry point of the family, and it's worth comparing it to the Pro Channel T2V node, because the knob sets genuinely differ: this one runs at 720P default (Pro Channel T2V defaults to 540P), has a seed (Pro Channel T2V doesn't), and has audio on by default (Pro Channel T2V defaults to off). The variants aren't cut from one template - check the widget on your node before assuming.

Cloud execution like every BizyTRD node: flip BizyAirPlus ON, Turbo runs on BizyAir's servers, and ComfyUI streams back the result. No local inference.

The inputs that matter

  • prompt - everything lives here; up to 5000 characters. Write motion, camera, mood.
  • resolution - 720P default.
  • duration - 1–16 seconds.
  • aspect_ratio - 16:9 default.
  • seed - 0 default, -1 = random. Lock it to reproduce a take.
  • audio - on by default: Q3 generates dialogue and SFX.

Shared BizyAir options: api_config (endpoint/key override) and skip_error (placeholder instead of abort).

Outputs

  • video - the finished clip, wired into preview or save.
  • request_id - cloud task ID.
  • urls - hosted result URLs.

How to install

cd /path/to/ComfyUI/custom_nodes
git clone https://github.com/siliconflow/BizyAirPlus.git
cd BizyAirPlus
python -m pip install -r requirements.txt

Restart ComfyUI (or install "BizyAirPlus" via ComfyUI Manager). Deps: bizyair-cloudberry and bizytrd; no model files. First run: account at bizyair.ai → API key → enter when the ON button prompts (or Settings > BizyAirPlus > API Key; key at ~/.BizyAirPlus/apikey.ini).

Where people get burned

The same trade as every Turbo node: you're trading fine-detail fidelity for speed and cost. For a first-pass idea this is the right tool; for a hero shot you'll want Pro. And since there's no style knob here (unlike some of the other Vidu nodes), you steer the look entirely through the prompt - be specific about lighting and atmosphere.

Pack note, one last time: BizyAir's malware reputation is leftover from a 2025 ComfyUI Manager auto-install bug - it's a legitimate SiliconFlow pack. If you ever remove it, pip uninstall bizyair-cloudberry bizytrd beats deleting the folder, which leaves packages behind.

CategoryBizyAirModelServices/BizyTRD/Vidu

Inputs (8)

NameTypeDefaultDescription
promptSTRINGVincenzo video prompt word, Max 5000 characters
resolutionCOMBO720POutput resolution, default 720P
durationINT51–16Video length (seconds) , range 1-16, default 5
aspect_ratiooptCOMBO16:9Output video aspect ratio, 16:9 by default
seedoptINT0-1–2147483647Random Seed, -1 indicates automatic random generation
audiooptBOOLEANtrueEnables the generation of audio with video (including dialogue and sound effects) , only Q3 model support
api_configoptBIZYAIR_OPENAPI_CONFIG单次请求覆盖base_url和api_key
skip_erroroptBOOLEANfalse开启后遇到错误不中断工作流,输出对应类型的错误占位符

Outputs (3)

NameTypeDescription
videoVIDEO
request_idSTRING
urlsSTRING