ComfyUI wrapper nodes for [a/WanVideo](https://github.com/Wan-Video/Wan2.1) and related models.

ComfyUI-WanVideoWrapper

Helper node to generate a list of floats that can be used to schedule cfg scale for the steps, outside the set range cfg is set to 1.0

CreateCFGScheduleFloatList

DownloadAndLoadWav2VecModel

Helper node to create empty Wan model to use with BasicScheduler -node to get sigmas

DummyComfyWanModelObject

Extracts the first N frames from a video sequence for continuations.

ExtractStartFramesForContinuations

FantasyPortraitFaceDetector

FantasyPortraitModelLoader

FantasyTalkingModelLoader

FantasyTalkingWav2VecEmbeds

LandmarksToImage

Loads Wan clip_vision model from 'ComfyUI/models/clip_vision'

LoadWanVideoClipTextEncoder

Loads Wan text_encoder model from 'ComfyUI/models/LLM'

LoadWanVideoT5TextEncoder

MultiTalkModelLoader

MultiTalkWav2VecEmbeds

QwenLoader


Visualizes the camera poses, from Animatediff-Evolved CameraCtrl Pose  
or a .txt file with RealEstate camera intrinsics and coordinates, in a 3D plot. 


ReCamMasterPoseVisualizer

WanVideoAddControlEmbeds

WanVideoAddExtraLatent

WanVideoAddFantasyPortrait

WanVideoAddStandInLatent

Adds NAG prompt embeds to original prompt embeds: 'https://github.com/ChenDarYen/Normalized-Attention-Guidance'

WanVideoApplyNAG

WanVideoATI_comfy

WanVideoATITracks

WanVideoATITracksVisualize

Comma separated list of blocks to apply block swap to, can also use ranges like '0-5' or '0,2,3-5' etc., can be connected to the dense_blocks input of 'WanVideoSetRadialAttention' node

WanVideoBlockList

Settings for block swapping, reduces VRAM use by swapping blocks to CPU memory

WanVideoBlockSwap

WanVideoClipVisionEncode

Context options for WanVideo, allows splitting the video into context windows and attemps blending them for longer generations than the model and memory otherwise would allow.

WanVideoContextOptions

WanVideoControlEmbeds

WanVideoControlnet

Loads ControlNet model from 'https://huggingface.co/collections/TheDenk/wan21-controlnets-68302b430411dafc0d74d2fc'

WanVideoControlnetLoader

WanVideoDecode

WanVideoDiffusionForcingSampler

EasyCache for WanVideoWrapper, source https://github.com/H-EmbodVis/EasyCache

WanVideoEasyCache

WanVideoEmptyEmbeds

WanVideoEncode

https://github.com/NUS-HPC-AI-Lab/Enhance-A-Video

WanVideoEnhanceAVideo

WanVideoExperimentalArgs

WanVideoFlowEdit

https://github.com/TianxingWu/FreeInit; FreeInit, a concise yet effective method to improve temporal consistency of videos generated by diffusion models

WanVideoFreeInitArgs

WanVideoFunCameraEmbeds

WanVideoImageClipEncode

Resizes image to the closest supported resolution based on aspect ratio and max pixels, according to the original code

WanVideoImageResizeToClosest

WanVideoImageToVideoEncode

Enables Multi/InfiniteTalk long video generation sampling method, the video is created in windows with overlapping frames. Not compatible or necessary to be used with context windows and many other features besides Multi/InfiniteTalk.

WanVideoImageToVideoMultiTalk

Rescale latents to match the expected range for encoding or decoding. Can be used to 

WanVideoLatentReScale

Looping through latent shift as shown in https://github.com/YisuiTT/Mobius/

WanVideoLoopArgs

WanVideoLoraBlockEdit

Select a LoRA model from ComfyUI/models/loras

WanVideoLoraSelect

WanVideoLoraSelectMulti

MagCache for WanVideoWrapper, source https://github.com/Zehong-Ma/MagCache

WanVideoMagCache

WanVideoMiniMaxRemoverEmbeds

WanVideoModelLoader

WanVideoPhantomEmbeds

WanVideoPromptExtender

WanVideoPromptExtenderSelect

WanVideoRealisDanceLatents

WanVideoReCamMasterCameraEmbed

WanVideoReCamMasterDefaultCamera

WanVideoReCamMasterGenerateOrbitCamera

WanVideoSampler

WanVideoScheduler

WanVideoSetBlockSwap

Sets the LoRA weights to be used directly in linear layers of the model, this does NOT merge LoRAs

WanVideoSetLoRAs

Sets radial attention parameters, dense attention refers to normal attention

WanVideoSetRadialAttention

WanVideoSLG


Patch WanVideo model to use TeaCache. Speeds up inference by caching the output and  
applying it instead of doing the step.  Best results are achieved by choosing the  
appropriate coefficients for the model. Early steps should never be skipped, with too  
aggressive values this can happen and the motion suffers. Starting later can help with that too.   
When NOT using coefficients, the threshold value should be  
about 10 times smaller than the value used with coefficients.  

Official recommended values https://github.com/ali-vilab/TeaCache/tree/main/TeaCache4Wan2.1:


<pre style='font-family:monospace'>
+-------------------+--------+---------+--------+
|       Model       |  Low   | Medium  |  High  |
+-------------------+--------+---------+--------+
| Wan2.1 t2v 1.3B  |  0.05  |  0.07   |  0.08  |
| Wan2.1 t2v 14B   |  0.14  |  0.15   |  0.20  |
| Wan2.1 i2v 480P  |  0.13  |  0.19   |  0.26  |
| Wan2.1 i2v 720P  |  0.18  |  0.20   |  0.30  |
+-------------------+--------+---------+--------+
</pre> 


WanVideoTeaCache

Bridge between ComfyUI native text embedding and WanVideoWrapper text embedding

WanVideoTextEmbedBridge

Encodes text prompts into text embeddings. For rudimentary prompt travel you can input multiple prompts separated by '|', they will be equally spread over the video length

WanVideoTextEncode

Encodes text prompts into text embeddings. This node loads and completely unloads the T5 after done,  
leaving no VRAM or RAM imprint. If prompts have been cached before T5 is not loaded at all.  
negative output is meant to be used with NAG, it contains only negative prompt embeddings.  

Additionally you can provide a Qwen LLM model to extend the positive prompt with either one  
of the original Wan templates or a custom system prompt.  


WanVideoTextEncodeCached

WanVideoTextEncodeSingle

Loads Wan VAE model from 'ComfyUI/models/vae_approx'

WanVideoTinyVAELoader

torch.compile settings, when connected to the model loader, torch.compile of the selected layers is attempted. Requires Triton and torch 2.5.0 is recommended

WanVideoTorchCompileSettings

WanVideoUni3C_ControlnetLoader

WanVideoUni3C_embeds

WanVideoUniAnimateDWPoseDetector

WanVideoUniAnimatePoseInput

WanVideoVACEEncode

VACE model to use when not using model that has it included, loaded from 'ComfyUI/models/diffusion_models'

WanVideoVACEModelSelect

Helper node to create start/end frame batch and masks for VACE

WanVideoVACEStartToEndFrame

Loads Wan VAE model from 'ComfyUI/models/vae'

WanVideoVAELoader

Alternative offloading method from DiffSynth-Studio, more aggressive in reducing memory use than block swapping, but can be slower

ComfyUI Extension: ComfyUI-WanVideoWrapper

Custom Nodes (81)