Google Veo3.1 Text To Video (Channel Edition)
Text-to-video at 1080p via BizyAir
- api_config
- video
- request_id
- urls
If the Fast tier of Veo 3.1 is the quick-and-cheap text-to-video node, this is the "make it look good" one. Veo 3.1 Pro, Channel Edition, text-to-video - same minimal shape as its Fast sibling, but the resolution dropdown defaults to 1080p instead of 720p. That single default change tells you what the Pro tier is for.
Veo 3.1 is Google's flagship video model and the closed benchmark the open-source community keeps sizing itself up against - with native audio generation as the capability open models genuinely haven't matched. Pro is the top tier: more fidelity, sharper motion, better handling of complex scenes, at a higher price and longer render. If you're making something that will actually be watched - a client piece, a music video, a short you're not embarrassed by - this is the node.
Why you'd reach for it
Because quality, not speed, is the point. The Channel Edition keeps the controls as simple as the Fast tier - prompt, resolution (1080p default), aspect_ratio (16:9 default) - so the only real difference is what you're paying for and waiting for. The trade-off is the usual one for this pack plus a time premium: closed, billed, cloud-rendered, and slower than Fast. For a one-off hero shot it's worth it; for a hundred-frame iteration pass, go Fast.
How it works
Type your video brief into prompt - scene, action, environment, camera movement, and audio cues, since Veo generates audio natively and rewards prompt detail. Pick resolution and aspect_ratio, queue. The node submits through BizyAir's channel to Veo 3.1 Pro, polls until the render completes, and returns video (VIDEO - wire it to Save Video or a preview node), request_id (STRING - trace/usage ID), and urls (STRING - clip location). Nothing runs locally.
The optional api_config (BIZYAIR_OPENAPI_CONFIG) input overrides base_url and api_key for a single request, and skip_error makes a failed call output a placeholder instead of aborting the workflow.
Install and setup
The same one-time install as every node in this pack:
cd 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). No model files - the bizyair-cloudberry and bizytrd pip packages auto-install on startup. Click the BizyAirPlus action-bar button to ON, get an API key from bizyair.ai, enter it, and queue.
Common issues
- Slow renders - Pro is billed and slow. Budget the wait, or drop to Fast for drafts.
- Resolution surprises - the dropdown is a choice between cost and output size; 1080p looks better and costs more. Match it to the deliverable.
- Prompt is everything - with no seed or negative prompt on this Channel Edition, a vague prompt returns a pretty-but-generic clip. Write the brief like you're directing.
Pack caveat: BizyAir auto-installs and sends your prompts to the cloud. Legitimate SiliconFlow product, but keep the switch OFF for local-only work.
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Video cue words | |
| resolution | COMBO | 1080p | Video resolution |
| aspect_ratio | COMBO | 16:9 | Picture scale |
| 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 | — |