Skip to main content
Wan 3.0 is Alibaba’s latest video generation model, now available in ComfyUI via Partner Nodes. It generates up to 30 seconds of video in a single pass with a synchronized audio track, and combines text prompts with reference images, videos, and audio for consistent characters and scenes.
To use the Partner Nodes, you need to ensure that you are logged in properly and using a permitted network environment. Please refer to the Partner Nodes Overview section of the documentation to understand the specific requirements for using the Partner Nodes.
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Key capabilities

  • Up to 30 seconds: Generates long clips with coherent motion and audio in a single pass
  • Native audio: Every output includes a synchronized audio track by default
  • Text, image, and reference input: Pure text prompts, first-frame animation, or up to 10 reference images, 5 reference videos, and 5 reference audio clips
  • Reference tags: Mention connected media directly in the prompt as @Image1, @Video1, or @Audio1
  • Flexible output: 480p, 720p, or 1080p resolution with adaptive, 16:9, 9:16, 1:1, 4:3, or 3:4 aspect ratios
  • Bilingual prompts: Prompt in English or Chinese

​
Wan 3.0 text-to-video workflow

Generate a video from a text prompt alone, with synchronized audio included by default.

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Wan 3.0” in Template Library

​
Prompting tips

  1. Duration: Set 2 to 30 seconds, or auto to let the model choose a duration that fits the prompt
  2. Resolution and ratio: The workflow ships at 720p with adaptive ratio; switch to 1080p or a fixed ratio like 16:9 for specific formats
  3. Audio: Audio is generated by default. Disable the audio option to get silent video
  4. Prompt extend: Prompt enhancement is on by default and rewrites your prompt for better results. Turn it off in advanced settings if you need exact wording

​
Wan 3.0 image-to-video workflow

Animate a single image into a video, with an optional last frame that the output transitions toward.

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Wan 3.0” in Template Library

​
Prompting tips

  1. First frame: The first_frame input is required. The last_frame input is optional, and the model generates the motion between the two
  2. Adaptive ratio: With adaptive, the output dimensions follow the input image
  3. Prompt: Describe what moves and how, plus the audio you want. Keep the subjects and composition unchanged unless you want the model to alter them

​
Wan 3.0 reference-to-video workflow

Generate a video conditioned on reference images, videos, and audio, with each reference assigned a job through tags in the prompt.

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Wan 3.0” in Template Library

​
Prompting tips

  1. Reference by tag: Refer to each input in the prompt as @Image1, @Video1, or @Audio1, numbered per type in input order. The sample prompt assigns the shoe design to @Image1 and the character to @Image2
  2. Limits: Up to 10 reference images, 5 reference videos, and 5 reference audio clips. Each reference video or audio clip must be 15 seconds or shorter, and the combined duration of all reference videos must stay within 15 seconds (same for audio). Total reference video plus output duration must not exceed 30 seconds
  3. Assign a job: State what each reference controls (product design, character identity, style, motion, voice) and what must stay unchanged. Explicit assignments produce more consistent results
  4. Prompt or reference required: Provide a prompt or at least one reference input, or the node returns an error

​
Get started

  1. Update ComfyUI to the latest version, or use the latest Comfy Desktop
  2. Go to Template Library, search for Wan 3.0
  3. Load one of the three workflows (text-to-video, image-to-video, or reference-to-video)
  4. Log in with your Comfy account and ensure you have enough credits
  5. Connect the input materials (first frame or reference images) and run

​
FAQs

Wan 3.0 is Alibaba’s latest video generation model, available in ComfyUI through Partner Nodes. It generates up to 30 seconds of video with synchronized audio in a single pass, and accepts text prompts, reference images, reference videos, and reference audio.
Up to 30 seconds per clip. The duration input accepts 2 to 30 seconds, or auto to let the model choose a duration that fits the prompt.
Yes. Every output includes a synchronized audio track by default, with dialogue, sound effects, and music generated together with the video. Disable the audio option for silent video.
Yes, in the reference-to-video workflow. Connect up to 10 reference images, 5 reference videos, and 5 reference audio clips, then refer to them in the prompt as @Image1, @Video1, or @Audio1.
Wan 3.0 is the newest generation of Alibaba’s video model. It extends the multimodal pipeline with reference tags for images, videos, and audio, native synchronized audio by default, and up to 30 seconds of output per clip. See the Wan 2.7 page for the previous generation.
Yes. The prompt input supports both English and Chinese.