MiniMax Hailuo 2.3 T2V Standard (Channel Edition)
Hailuo 2.3 standard text-to-video with optimizer and watermark controls
- api_config
- video
- request_id
- urls
The standard-tier text-to-video node for MiniMax Hailuo 2.3, channel edition. Prompt in, video out, with three extra switches the Fast variant doesn't give you: prompt_optimizer, aigc_watermark, and fast_pretreatment. It's the "I want Hailuo's best quality and I'm willing to pay for the standard tier" option - and the natural upgrade path once you've outgrown the Fast node.
Text-to-video is where the standard tier's prompt optimizer earns its keep. You type something flat like "a dog runs through a field," the service rewrites it into a proper cinematic shot description, and the motion comes out noticeably better. If you're new to writing video prompts - which is a different skill from image prompts, heavy on camera language - this node quietly fixes your worst prompts for you.
How it works
BizyTRD cloud wrapper: prompt (required, up to 2000 chars, "conch mirror instruction writing" supported) to the BizyAir channel, VIDEO back. resolution supports 768P and 1080p, with the standard caveat that only 768P runs at 10 seconds; duration is a combo defaulting to 6.
The extra controls, per the tooltips: prompt_optimizer rewrites/optimizes the prompt before generation (schema default off, despite the tooltip's "turned on by default" wording - flip it on if you want it); aigc_watermark adds the AI-generated watermark (default off); fast_pretreatment shortens the prompt-optimization time when you need speed. api_config overrides the endpoint and key per request; skip_error outputs a placeholder instead of aborting the workflow.
Inputs and outputs
prompt(required, multiline).resolution(default768P),duration(default 6).- Optional:
prompt_optimizer,aigc_watermark,fast_pretreatment,api_config,skip_error. - Outputs:
video(VIDEO),request_id,urls.
Installing BizyAirPlus
ComfyUI Manager: "BizyAirPlus", or:
cd /path/to/ComfyUI/custom_nodes
git clone https://github.com/siliconflow/BizyAirPlus.git
cd BizyAirPlus
python -m pip install -r requirements.txt
Restart, account at bizyair.ai, API key, BizyAirPlus button ON. Dependencies: bizyair-cloudberry, bizytrd.
Common issues
Standard pack fare: missing button → dependency environment (pip show bizyair-cloudberry), cloud failures → key/network/console, and metered pricing. The tier-specific gotchas are the 1080p-at-10s limitation and the fact that the prompt optimizer adds a noticeable step to every run - if a generation feels slow, prompt_optimizer + fast_pretreatment is the first place to look. The standard tier out-prices Fast, so if quality isn't the bottleneck, the Fast T2V node is the cheaper habit.
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Video generation prompt words, maximum 2000 characters; support conch mirror instruction writing. | |
| resolution | COMBO | 768P | Supports 768P, 1080p; only 768P is supported when the duration is 10 seconds. |
| duration | COMBO | 6 | 6 seconds, 10 seconds; 1080P only supports 6 seconds. |
| aigc_watermarkopt | BOOLEAN | false | Whether to add AI generated watermark in the video, the default off. |
| prompt_optimizeropt | BOOLEAN | false | Whether to automatically optimize prompt, turned on by default. |
| fast_pretreatmentopt | BOOLEAN | false | Whether to shorten the prompt optimization time-consuming, the default off. |
| 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 | — |