> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.
# Wan 3.0 Video Generation in ComfyUI
> Learn how to use Wan 3.0 via Partner Nodes in ComfyUI for text-to-video, image-to-video, and reference-to-video generation with synchronized audio
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](/tutorials/partner-nodes/overview) section of the documentation to understand the specific requirements for using the Partner Nodes.
Make sure your ComfyUI is updated.
* [Download ComfyUI](https://www.comfy.org/download)
* [Update Guide](/installation/update_comfyui)
Workflows in this guide can be found in the [Workflow Templates](/interface/features/template).
If you can't find them in the template, your ComfyUI may be outdated.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
* [Cloud](https://cloud.comfy.org) will update after ComfyUI stable release.
So, if you find any core node missing in this document, it might be because the new core nodes have not yet been released in the latest stable version. Please wait for the next stable release.
## 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.
Open in Comfy Cloud
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.
Open in Comfy Cloud
Download JSON or search "Wan 3.0" in Template Library
Input materials
Download this sample input image to try the workflow:
First frame for the workflow, or use your own image.
#### 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.
Open in Comfy Cloud
Download JSON or search "Wan 3.0" in Template Library
Input materials
Download these sample input images to try the workflow:
Reference image for the product in the video.
Reference image for the character in the video.
#### 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](https://www.comfy.org/download)
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](/interface/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](/tutorials/partner-nodes/wan/wan2-7) for the previous generation.
Yes. The prompt input supports both English and Chinese.