A set of ComfyUI workflows for WAN Video:
I highly recommend using Torch Compile and Sage Attention (set as “SageAttention_Compiled” in the model loaders). The TorchCompile node and SageAttention are enabled by default.
If you don’t have them installed, you can bypass the TorchCompile node and use SDPA instead of Sage Attention - it will be slower, but it will work.
VACE WAN 2.2 Depth Control
WAN 2.1 I2V
WAN 2.1 T2V
WAN 2.2 FaceEnhance
WAN 2.2 I2V StartEnd Frames
WAN 2.2 I2V
WAN 2.2 LORA COMPARE
WAN 2.2 S2V
WAN 2.2 T2I
WAN 2.2 T2V
WAN ANIMATE 2.2
WAN 2.2 FASTWAN 5B ControlNetDepth
WAN 2.2 FASTWAN 5B I2V
WAN 2.2 FASTWAN 5B T2V
FlashVSR FaceEnhance
FlashVSR UPSCALE
WAN 2.1 FantasyPortrait
WAN 2.2 I2V FAST EFFICIENT BATCH
WAN T2I 2.2 FAST EFFICIENT BATCH
WAN T2V 2.2 FAST EFFICIENT BATCH
WAN 2.2 UPSCALE + FACE ENHANCE
WAN 2.2 UPSCALE
WAN 2.2 FunCameraControl I2V
WAN 2.2 FunControl
WAN 2.2 MANUAL FunCameraControl I2V
".png contains workflows, you can drag and drop them like .json in your ComfyUI interface"
Some workflows uses Subgraphs, on your .bat launcher set:
--front-end-version Comfy-Org/ComfyUI_frontend@latest
Make sure to update your Kijai nodes and CRT-Nodes
You can find better scaled versions here
This is my RUNPOD referal link to earn 5$, wich is about 6h of free RTX 5090 usage : https://runpod.io?ref=u7b2habt
It also helps me to train new models, thanks.
Description
v1.8.4
-Added back WAN 2.2 I2V (LOOP) as requested (Updated)
v1.8.3
-Minimal fix on the 2.2 I2V lora stack order
v1.8.2
-Added WAN 2.2 T2I + VAE UPSCALE (native)
-Added WAN 2.2 T2I + VAE UPSCALE
https://github.com/spacepxl/ComfyUI-VAE-Utils
v1.8.1
-Add LoRA stack loaders (to avoid confusion)
v1.8.0
-Correct 2.2 T2V sigma 0.9 to 0.875
v1.7.9
- (Fix) 2.2 I2V was overriten by T2V workflow
v1.7.8
-Moved loaders into subgraphs
-Added WAN 2.2 UPSCALE + FACE ENHANCE
-Added WAN 2.2 UPSCALE
v1.7.7
-Update WAN 2.2 Batch Sampler
v1.7.6
-Added FlashVSR FaceEnhance
-Added FlashVSR UPSCALE
v1.7.5
-Quantize resize
-Sigma to step
-Inference shift according to WAN official config
v1.7.2
-Updated FAST EFFICIENT BATCH node (T2I save image if framecount is 1, disable FETA if framecount is 1, Add tiled decode option, add metadata to saved files)
v1.7.1
-Added WAN MANUAL 2.2 FunCameraControl I2V
v1.7.0
-DepthAnything Automatic Download
v1.6.8
-Update Model Loaders, Default settings
v1.6.8
-Added WAN 2.2 S2V
-Added WAN 2.2 T2I FAST EFFICIENT BATCH (RandomPrompts)
-Added WAN 2.2 T2I FAST EFFICIENT BATCH
v1.6.7
-Rework
WAN 2.2 FAST EFFICIENT BATCH (RandomPrompts)
WAN 2.2 FAST EFFICIENT BATCH
WAN 2.2 LORA COMPARE
WAN 2.2 T2I
v1.6.6
-Added WAN 2.2 FAST EFFICIENT BATCH (RandomPrompts)
v1.6.5
-Added WAN 2.2 FAST EFFICIENT BATCH
v1.6.4
-Fix end step on WAN 2.1 I2V
v1.6.3
-Added WAN 2.2 LORA COMPARE
v1.6.2
-Added WAN 2.1 I2V
v1.6.1
-Added WAN 2.1 FantasyPortrait
-Rework WAN 2.2 T2I
v1.6.0
-Added WAN 2.2 Fun InP StartEnd Frames
-Added WAN 2.2 FunCameraControl I2V
-Added WAN 2.2 FunControl
v1.5.8
-Added WAN 2.1 Ip-Adapter
v1.5.8
-Added WAN 2.2 FASTWAN 5B ControlNetDepth
-Added WAN 2.2 FASTWAN 5B I2V
-Added WAN 2.2 FASTWAN 5B T2V
v1.5.7
-Added T2V (LOOP)
v1.5.6
-Added WIP Subgraph workflow
-Added lightx2v 2.2 to the I2V and I2V Loop workflows
v1.5.5
-Added WAN 2.1 FaceEnhance
v1.5.4
-Added WAN 2.2 FaceEnhance (Update CRT-Nodes)
-Changes made according to new Kijai update (VAE and torchcompile)
-ALT Versions are the new main ones
-Replaced all 2.1 Lightx2v with the new 2.2 version see in description for the link
v1.5.3
-Initial settings tweaks
v1.5
-Added T2I
-Added VACE WAN 2.2 (VideoDepth)
v1.4
-New feature on the sampler, setting second sampler output to denoised
v1.3
-Added WAN 2.1 DFORCE I2V (LOOP) + LLM Prompt Enhance
-Added WAN 2.1 DFORCE I2V (LOOP)
-Added WAN 2.1 DFORCE T2V (LOOP) + LLM Prompt Enhance
-Added WAN 2.1 DFORCE T2V (LOOP)
-Added WAN 2.2 I2V (LOOP) + LLM Prompt Enhance
-Added WAN 2.2 I2V (LOOP)