Nodes/BizyAirPlus/Alibaba Wan 2.6 Image To Video (Official Edition)
ComfyUI Node

Alibaba Wan 2.6 Image To Video (Official Edition)

Alibaba's newer closed model, reachable only through the cloud

By siliconflow·Created 5 months ago·Updated about a month ago· 20
Alibaba Wan 2.6 Image To Video (Official Edition)
  • image
  • api_config
  • video
  • request_id
  • urls
resolution480P
duration5
prompt_extendtrue
prompt
audio_url
audiotrue
skip_errorfalse

Wan 2.6 is what Alibaba shipped after 2.5, and like 2.5 it never got weights - the numbered series went API-only after the open Wan 2.2, and that's just the business model now. This node is one of the few doors into the 2.6 image-to-video model, and it's basically Wan 2.5's node with a newer engine and one small input change you should know about.

What this node does

BizyTRD_Wan_2_6_Official_I2V_API takes an image first frame and generates a video on Wan 2.6, running on BizyAir's servers. Flip BizyAirPlus ON, upload your still, and the clip streams back into ComfyUI. Cloud execution like every BizyTRD node - no local model, no VRAM bill, and no way to run it any other way.

The inputs that matter

  • image - the first frame; output aspect ratio tries to follow it.
  • resolution - combo defaults to 480P with the tooltip mentioning a 1080P default; the model auto-scales to the nearest total-pixel bucket, so treat it as a ballpark.
  • duration - 5 or 10 seconds.
  • prompt_extend - on by default: an LLM rewrites/expands your prompt, big win for short prompts, costs time. Off it if you write your own detailed prompts.
  • prompt - optional, up to 1500 characters.
  • audio_url - here's the change from 2.5: instead of an AUDIO socket, this node takes a URL string (WAV/mp3, 3–30s, up to 15MB) for custom audio that drives the video and replaces auto-dubbing. Paste a hosted file's URL rather than uploading.
  • audio - on by default: auto-generates background music or SFX; flip off for silent. A provided audio_url takes precedence.

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

Outputs

  • video - the finished clip; wire 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; key at ~/.BizyAirPlus/apikey.ini).

Where people get burned

The audio_url switch trips people who used the 2.5 node: 2.5 takes an AUDIO socket, 2.6 takes a URL string, so a workflow wired for one won't just drag across. Also, don't expect to compare 2.6 against a local 2.2 checkpoint head-to-head - different pipelines entirely, and 2.6 is a closed API model with its own behavior. And keep prompt_extend in mind as a latency toggle, not a quality guarantee.

Pack note: BizyAir's malware reputation is leftover from a 2025 ComfyUI Manager auto-install bug - legitimate SiliconFlow pack; if you ever remove it, pip uninstall bizyair-cloudberry bizytrd rather than deleting the folder alone.

CategoryBizyAirModelServices/BizyTRD/Wan Video

Inputs (9)

NameTypeDefaultDescription
imageIMAGEInput first frame picture, output video aspect ratio will try to keep consistent with the first frame picture
resolutionCOMBO480PThe model automatically scales to the nearest total pixel according to the video resolution range. WAN2.5-I2V default 1080P
durationINT55–10Video length in seconds. Wan2.5-i2v-preview 5 or 10 seconds
prompt_extendBOOLEANtrueWhether prompt smart overwrite is enabled. After opening, use the large model to optimize the input prompt, improve the effect of short prompts obviously, but it will increase the time-consuming
promptoptSTRINGThe picture lives the video prompt word. Wan2.6/2.5 Max 1500 characters, wan2.2/Wanx2.1 Max 800 characters. This parameter is not valid when using video effects
audio_urloptSTRINGCustomize the audio URL that the model will use to generate the video. Support for WAV/mp3,3-30 seconds, up to 15MB. It will replace auto-dubbing when available. Wan2.6/2.5 support only
audiooptBOOLEANtrueWhether to automatically generate background music or sound effects. True: automatically generates audio based on video content; false: generates silent video. The audio parameter takes precedence over audio and outputs the silent video even when audio = false
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