MiniMax Hailuo 2.3 I2V Standard (Channel Edition)
Hailuo 2.3 standard I2V with prompt optimization built in
- first_frame_image
- api_config
- video
- request_id
- urls
The standard tier of MiniMax Hailuo 2.3 image-to-video, channel edition. Where the Fast variant strips options down to prompt, frame, resolution and duration, this one adds three quality-of-life controls: a built-in prompt optimizer, an AIGC watermark toggle, and a "fast pretreatment" speed option. If you want Hailuo's best quality and don't mind the model second-guessing your prompt, this is the I2V node to use.
The killer feature here is prompt_optimizer. Hailuo's standard tier will rewrite and enrich your prompt before generating - which mostly means better motion and composition than whatever you typed, at the cost of it not being literally your words. That's the same trade a lot of hosted video models make, and it's usually worth it unless you're being very precise on purpose.
How it works
BizyTRD cloud wrapper: first_frame_image (required) plus prompt (required, up to 2000 chars, "conch mirror instruction writing" supported) goes to the BizyAir channel; an edited VIDEO comes back. resolution supports 768P and 1080p, but only 768P is available at 10 seconds; duration is a combo defaulting to 10 seconds here (the I2V standard defaults longer than the T2V variant).
The extra controls, straight from the tooltips:
prompt_optimizer- whether the service auto-optimizes your prompt. Note the schema default is off even though the tooltip says "turned on by default"; if you want the rewrite, flip it on explicitly.aigc_watermark- whether to add the AI-generated watermark to the video (default off).fast_pretreatment- whether to shorten the prompt-optimization time (default off); useful when you want the optimizer but are in a hurry.
api_config overrides base_url/api_key per request; skip_error outputs a placeholder instead of aborting the workflow.
Inputs and outputs
first_frame_image(required) - the frame to animate.prompt(required, multiline).resolution(default768P),duration(default 10).- 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
Same frame constraints as the Fast I2V (under 20 MB, short edge over 300 px, aspect between 2:5 and 5:2), and the same 1080p-only-at-6s resolution coupling. The standard tier costs more than Fast, and the prompt optimizer adds latency on top - if your run feels slow, check whether prompt_optimizer and fast_pretreatment are set the way you think they are. Then the pack's usual: dependency environment for a missing button, console for cloud errors.
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| first_frame_image | IMAGE | Input first frame image for image-to-video generation | |
| 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 | 10 | 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 | — |