Vidu Q3 Pro Text To Video (Channel Edition)
Vidu Q3 Pro text-to-video, Channel edition — the cheapest way into Q3
- api_config
- video
- request_id
- urls
Want to know what all the Vidu Q3 fuss is about without committing much wallet? This is the node. Text-to-video, no image to prep, no seed to manage - the Channel (Base) edition of Vidu Q3 Pro in its most stripped-down form.
What this node does
BizyTRD_Vidu_Q3_Pro_Base_T2V_API turns a prompt into a video clip, full stop. It's the T2V member of the Q3 Pro family in BizyAirPlus, and in the Channel edition it's deliberately bare: no seed control, no recommendation-prompt upsell, no off-peak mode. You get prompt, resolution, duration, style, aspect ratio, and an audio toggle. That's it.
It's cloud execution like every BizyTRD node - flip BizyAirPlus ON and Vidu Q3 Pro runs on BizyAir's servers while ComfyUI streams back progress. Your GPU just sits there.
The inputs that matter
prompt- everything is this field. Write motion, camera, subject, mood: "slow dolly-in on a neon diner at night, rain on the window, a waitress wipes a counter."resolution- note the default here is 540P, not the 720P the other Vidu nodes default to. Fine for tests; bump it when you like a take.duration- 3–15 seconds.style-generaldefault.aspect_ratio- 16:9 default.audio- the one real surprise: off by default in this node, unlike its siblings. Q3 can generate synchronized audio, but on the Channel T2V you have to ask for it explicitly. Flip it on if you want dialogue and SFX.
Shared BizyAir options: api_config (endpoint/key override per request) and skip_error (error placeholder instead of workflow abort).
Outputs
video- the finished clip, wired into a preview or save node.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" through ComfyUI Manager). Deps: bizyair-cloudberry and bizytrd; no model files. First run: account at bizyair.ai → API key → enter when the ON button prompts (Settings > BizyAirPlus > API Key works; key at ~/.BizyAirPlus/apikey.ini).
Where people get burned
The silent-by-default audio is the sneaky one - most of the other Vidu nodes default to audio on, so it's easy to assume this one does too and wonder why your clip came out mute. Check the toggle before you queue.
Second, T2V is the weakest mode for consistency. If your clip's subject drifts, that's the nature of text-only generation; anchoring a first frame with the I2V or FLF nodes is the fix, not a better prompt. And on the pack: BizyAir's malware reputation is leftover from a 2025 ComfyUI Manager auto-install bug - legitimate SiliconFlow pack, removed properly with pip uninstall bizyair-cloudberry bizytrd.
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Prompt words for video generation | |
| resolution | COMBO | 540P | Output resolution |
| duration | INT | 53–15 | Video length in seconds |
| style | COMBO | general | Style of video generation |
| aspect_ratioopt | COMBO | 16:9 | Aspect ratio of video |
| audioopt | BOOLEAN | false | Whether to use audio and video straight out capability |
| api_configopt | BIZYAIR_OPENAPI_CONFIG | 单次请求覆盖base_url和api_key | |
| skip_erroropt | BOOLEAN | false | 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)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| request_id | STRING | — |
| urls | STRING | — |