Skip to content
BytePlusBytePlusBytePlus ModelArk for ComfyUI

Virtual Portrait - New Asset

Template
Virtual Portrait - New Asset, in the ComfyUI template browser under BytePlus
Workflow file
Virtual Portrait - New Asset.json
BytePlus nodes
Create Image Asset, Seedance 2.5 Reference to Video
Keys needed
ModelArk API key, IAM access key and secret key
Also uses
Load Image, Preview as Text, Save Video (built into ComfyUI)

What it makes

Section titled “What it makes”

One 5 second video, plus a new asset in your library. The template uploads a picture as a virtual portrait named “My portrait” and passes it to Seedance 2.5 Reference to Video as asset1, with the prompt “asset1 walks along a beach at sunset, turns toward the camera and smiles. Waves, soft wind, cinematic lighting.” The shipped picture is the ComfyUI logo, so replace it with your own portrait image.

The workflow

Section titled “The workflow”
The Virtual Portrait New Asset template: Load Image into Create Image Asset, then Seedance 2.5 Reference and Save Video
Load Image, Create Image Asset, Seedance 2.5 Reference to Video, Save Video and an Asset details preview.
  1. Portrait image (Load Image) supplies the picture.
  2. Create Image Asset uploads it to Comfy.org storage, finds or creates the virtual portrait group “ComfyUI Virtual Portraits”, creates the asset “My portrait” and waits until it is Active (wait_until_active is on). Its asset_id goes to asset_1 and its info goes to an Asset details preview.
  3. Seedance 2.5 Reference to Video uses model Seedance 2.5 at 720p and 16:9 for 5 seconds with generate_audio on and task_type reference.
  4. Save Video keeps the clip under BytePlus/Video/Seedance_new_asset.

Run it

Section titled “Run it”
  1. Add your ModelArk API key and the IAM access key and secret key in Settings → BytePlus if you have not yet (API keys). The IAM keys need asset-library permission, and your account also needs Dreamina Seedance Advanced Creation Rights.
  2. Log in to your Comfy.org account in ComfyUI. A connected image is uploaded to Comfy.org storage first, because creating an asset takes a link.
  3. Open the template browser and choose Virtual Portrait - New Asset under BytePlus.
  4. In Portrait image, pick your own portrait.
  5. Press Run. The asset details appear first and the video follows when Seedance finishes.

Settings worth changing

Section titled “Settings worth changing”
  • asset_name and group_name: name the asset and its group. Use one group per person. An existing group_id adds the asset to a group you already have.
  • image_url: an advanced input. A public HTTPS link replaces the image and skips the Comfy.org upload.
  • Prompt: keep asset1 where the person should appear and describe the action around it.
  • resolution, ratio and duration: change the size and length of the clip.
  • wait_until_active: keep it on so Seedance only starts once the asset is usable.

Example result

Section titled “Example result”
The result panel: the saved video file name, three frames of the video and the asset details as JSON with the asset and group IDs hidden
Example result, made with the ComfyUI logo as the picture.
The video from this example.

Time and cost

Section titled “Time and cost”

Each generation bills one Seedance 2.5 video. Registering the asset is cached per image content, so running again with the same picture reuses the asset. The Seedance seed control is set to randomize, so every run makes a new clip and bills again. Set it to fixed and ComfyUI reuses the cached result of an unchanged workflow without billing. Only use media you are authorized to use.

Section titled “Related”