Wan Animate 2 Motion Transfer
Wan-Animate-2 turns one still into powerful full-body motion - no skeletons.
AI model workflow
WAN ComfyUI Workflows
Create video from text or images with WAN in ComfyUI. Use dedicated animation and editing workflows to transfer character motion, guide opening and ending frames, or rework existing footage. Run them on RunComfy Cloud, download workflow JSON, or deploy supported workflows as APIs.
51 workflows
Featured workflow
Wan 2.2 | Open-Source Video Gen Leader
The workflows
51 WAN ComfyUI Workflows
Compare WAN ComfyUI examples by input and result: a new video, animated character, or edited clip. Open a workflow to check its Wan version, references, and instructions. Run it on RunComfy Cloud, download the workflow JSON, or deploy supported workflows as APIs.
Wan Dancer Music-to-Dance
Turns image and music into perfectly synced dance videos fast.
Wan 2.2 Animate Character/Pose/Background V3
Swap characters, poses, and scenes fast with total creative control.
Wan 2.2 Smooth v5.0
Turn text or images into silky-smooth short videos instantly.
InfiniteTalk Lip-Synced Avatars
Photo + Voice = Perfectly Synced Talking Avatar in Minutes
Wan 2.2 Animate Character Swap & Lip-Sync
Transforms any face to speak and move like the original with ease.
Wan 2.2 First-Last Frame to Video
Generate smooth videos from a start and end frame using Wan 2.2 FLF2V.
Wan 2.2 Animate Action Transfer V7
Makes your characters move exactly like real people—fast and controlled.
Wan 2.2 Lightning 4-Step T2V & I2V
Wan 2.2 now 20x faster! T2V + I2V in 4 steps.
Wan 2.2 VBVR Video Reasoning
Creates smart, consistent videos with real scene logic and structure.
Stable Video Infinity 2.0 Long Video
Create long, smooth, story-driven AI videos effortlessly.
Wan 2.2 Low VRAM (Kijai)
Low VRAM. No longer waiting. Kijai wrapper included.
Wan 2.2 Lightx2v V2 I2V & T2V
Dual Light LoRA setup, 4X faster.
VACE 14B Video Creation & Editing
Create, edit and transform videos with the powerful VACE Wan2.1 14B.
Wan 2.2 Animate V2 Pose Video
Transforms photos into smooth-motion animated character videos using Wan 2.2.
Wan 2.1 Video Generation
Create incredible videos from text or images with breakthrough AI running on everyday CPUs.
Wan Alpha Transparent Video
Alpha magic: instant transparent background videos for VFX and design.
Wan 2.2 Video Generation
Available now! Better precision + smoother motion.
Create Coherent Story Scenes
Build seamless storytelling scenes with rich visual consistency.
Wan 2.1 Fun ControlNet
Generate videos with ControlNet-style visual passes like Depth, Canny, and OpenPose.
Pose Control LipSync S2V
Turn images into talking, moving characters with pose and audio control.
Wan 2.2 Qwen Multiangle Split Stack
Turn one image into synced multi-angle animated videos fast.
MultiTalk Multi-Speaker Lip Sync
One-click create multi-speaker lip-sync videos from portraits and voices!
Wan 2.2 VACE Fun Image-to-Video
Turn still photos into lifelike animated videos with custom prompts.
Wan 2.2 Sound-to-Video
Turns your audio clip into lifelike, synced video from one image
Instagirl v.20 (Wan 2.2 LoRA)
A Wan 2.2 workflow for demoing the Instagirl LoRA by Instara.
Wan 2.1 Ditto Video Restyle
Transform videos into stunning artistic styles with perfect motion flow.
Wan 2.2 VACE Pose Control
Turn still images into stunning motion with pose-based control.
Wan 2.2 Image Generation (2-in-1)
MoE Mix + Low-Only with upscale. Pick one.
Wan 2.2 First-Frame Video Restyle
Change the first frame, folks, your style makes the whole video look amazing. Pure magic.
Wan 2.1 Stand In Character Video
Keeps characters consistent across video from just one reference image.
Wan 2.1 Fun I2V & T2V
Empower your AI videos with Wan 2.1 Fun.
32 of 51 workflows shown
About WAN
What can WAN do in ComfyUI?
WAN in ComfyUI supports text-to-video and image-to-video generation, with specialized workflows for character animation and video editing. Its broader ecosystem adds reference motion, speech-driven performances, and controls for transforming existing footage.
Choose Wan 2.2 text-to-video or image-to-video for general creation. Wan Animate examples focus on animation and replacement, S2V examples use speech as an input, and VACE examples provide video editing controls. Wan 2.1 remains the base for several specialized workflows.
The input matters as much as the model name. A driving video controls a different kind of result from an audio track or a pair of keyframes. Talking-avatar, dance, and story-video pipelines may add other models or controls; open their detail pages for the exact requirements.
References and model resources: Wan2.2 GitHub, Wan2.1 GitHub, Explore WAN models on Hugging Face, Explore WAN models on Civitai.
Capabilities
Explore WAN capabilities in ComfyUI
Explore prompt and image generation alongside dedicated motion-transfer, lip-sync, keyframe, and video-editing setups. Select the controls that match your available inputs.
Text-to-video and image-to-video
Generate a new clip from a written scene or animate a source image.
Character animation and motion transfer
Guide a character's movement with a dedicated Wan animation setup.
Character replacement and lip sync
Transfer a performance into a different character with a dedicated replacement setup.
First-and-last-frame control
Use opening and ending images to guide the progression of a clip.
Video editing and restyling
Rework existing footage with a VACE setup built for guided video edits.
WAN models on RunComfy
Create WAN video without local model setup
Use a prepared Wan setup in ComfyUI to work with your own prompts, images, audio, or driving footage. Choose a cloud GPU for the selected model and video size. Download the JSON when you want to reproduce the setup locally with its required files.
Run a WAN workflow nowEditable video inputs
Adjust the prompts, images, speech, or driving footage required by the selected Wan example.
Reference and model assets
Keep compatible models and supporting assets with the cloud setup for reuse.
Prepared dependencies
Start with the example's configured dependencies, including the tools used for specialized video tasks.
Cloud GPU options
Choose GPU memory for the model format, resolution, frame count, and control stages you use.
Applications
What you can make with WAN
Find an example for an animated photo, talking avatar, dance clip, story scene, or restyled video.
Photo Animation
Create a moving character scene from an image and the inputs required by the selected Animate setup.
Talking Avatars
Pair a portrait with speech in an InfiniteTalk pipeline for an audio-driven character video.
AI Dance Videos
Combine an image and music in a Wan Dancer setup to develop a dance performance.
Cinematic Camera Shots
Explore camera-guided movement from a still image with a Wan Fun Camera setup.
Story Scenes
Combine Qwen image edits with Wan video generation to develop related visual scenes.
Video Restyling
Reinterpret existing footage in a new visual style with a dedicated Ditto pipeline.
Frequently asked questions
WAN in ComfyUI: FAQ
Choose a Wan model and input type, understand Animate, S2V, and VACE options, and check what you need for cloud or local use.
What WAN ComfyUI workflow should I start with?
Use a Wan 2.2 generation example for a new video from text or an image. For an existing performance or clip, choose an animation, replacement, or video-editing setup instead. Start with the input you already have rather than choosing the most complex workflow.
Should I use Wan 2.2 or Wan 2.1?
Wan 2.2 is a starting point for general generation and several newer animation setups. Wan 2.1 remains the base for specialized examples such as VACE editing and some talking-avatar pipelines. Choose the demonstrated result and its listed version; supporting files and add-ons are not universally interchangeable.
Can Wan 2.2 make lip-sync or speech-to-video?
Yes. Dedicated S2V setups use an image and audio for speech-driven performance. Other lip-sync examples transfer a performance from reference footage. Check whether the selected setup expects speech, a driving video, or both; basic image-to-video does not provide the same control.
What is Wan Animate used for?
Wan Animate setups guide character animation or replacement using reference inputs. The character swap and lip-sync example is one specific performance-transfer option. Follow the input requirements of the example rather than assuming every Animate version uses the same controls.
What is VACE in a WAN ComfyUI workflow?
VACE provides guided video creation and editing options within the Wan ecosystem. Use the VACE video-editing example when the task involves transforming or controlling footage. Its detail page explains the supported inputs and edit modes.
How do I keep a character consistent in WAN videos?
Use a setup designed around references, character replacement, or a compatible LoRA. Consistency can still drift across shots, so inspect the face, outfit, and scene details rather than assuming a shared model guarantees a perfect match. Story pipelines may combine image editing and video generation.
How much VRAM do I need for Wan 2.2 in ComfyUI?
Memory needs depend on the model format, video resolution, frame count, and additional controls. Check the selected example's requirements instead of using one VRAM estimate for every Wan 2.2 setup. Run it on a suitable cloud GPU, or download the JSON and prepare those dependencies locally.
Related resources
More ways to use WAN
Train a WAN LoRA with a supported Wan 2.1 or Wan 2.2 base model, or open a matching RunComfy Models page for direct generation.
Train a Wan 2.1 1.3B LoRA
Use the smaller Wan 2.1 text-to-video base for a lighter custom video LoRA training path.
Open Wan 2.1 1.3B TrainerTrain a Wan 2.1 14B LoRA
Train a higher-capacity Wan 2.1 text-to-video LoRA for reusable motion or visual concepts.
Open Wan 2.1 14B TrainerTrain a Wan 2.1 I2V 480P LoRA
Train against the Wan 2.1 14B image-to-video 480P base when a source image drives the clip.
Open I2V 480P TrainerTrain a Wan 2.1 I2V 720P LoRA
Use the Wan 2.1 14B image-to-video 720P base for higher-resolution image-driven training.
Open I2V 720P TrainerTrain a Wan 2.2 14B T2V LoRA
Train a custom text-to-video LoRA on the Wan 2.2 14B base.
Open Wan 2.2 T2V TrainerTrain a Wan 2.2 14B I2V LoRA
Train a Wan 2.2 image-to-video LoRA for concepts driven by a reference image.
Open Wan 2.2 I2V TrainerTrain a Wan 2.2 TI2V 5B LoRA
Use the unified 5B base for a smaller Wan 2.2 text-and-image-to-video training path.
Open Wan 2.2 5B TrainerUse WAN models directly
Open the WAN Models page when you want direct generation instead of a complete workflow graph.
Browse WAN ModelsExplore Wan 2.2 models
Compare models and generation options grouped specifically around Wan 2.2.
Browse Wan 2.2 ModelsExplore Wan 2.5 models
Open the Wan 2.5 Models page for direct access to the newer model line where available.
Browse Wan 2.5 Models