floyo logo
Powered by
ThinkDiffusion
⚡️Nano Banana 2 ⚡️ just landed. Start creating now.
floyo logo
Powered by
ThinkDiffusion
⚡️Nano Banana 2 ⚡️ just landed. Start creating now.

Video to Video Restyle with Wan

Create a new video by restyling an existing video with a reference image.

446

Generates in about 10 mins 47 secs

Nodes & Models

GetNode
UNETLoader
flux1-dev-fp8.safetensors
DualCLIPLoader
clip_l.safetensors
t5xxl_fp8_e4m3fn.safetensors
VAELoader
Note
Label (rgthree)
PrimitiveInt
Fast Groups Muter (rgthree)
Fast Groups Bypasser (rgthree)
LoadImage
CLIPTextEncodeFlux
PreviewImage
SetNode
ImageBlend
EmptyLatentImage
VAEDecode
SaveImage
WanVideoTeaCache
WanVideoSLG
WanVideoLoraSelect
Wan/wan_i2v_720_l1v3w4llp4p3r_e50_with_trigger.safetensors
WanVideoModelLoader
Wan2.1-Fun-Control-14B_fp8_e4m3fn.safetensors
WanVideoVAELoader
wan_2.1_vae.safetensors
LoadWanVideoT5TextEncoder
umt5_xxl_fp16.safetensors
LoadWanVideoClipTextEncoder
open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors
WanVideoTextEncode
WanVideoEncode
WanVideoControlEmbeds
WanVideoClipVisionEncode
WanVideoImageToVideoEncode
WanVideoSampler
WanVideoDecode
LoadFluxControlNet
flux-depth-controlnet-v3.safetensors
ApplyFluxControlNet
XlabsSampler
WanVideoLoraSelect
Wan/wan_i2v_720_l1v3w4llp4p3r_e50_with_trigger.safetensors
WanVideoModelLoader
Wan2.1-Fun-Control-14B_fp8_e4m3fn.safetensors
WanVideoVAELoader
wan_2.1_vae.safetensors
LoadWanVideoT5TextEncoder
umt5_xxl_fp16.safetensors
LoadWanVideoClipTextEncoder
open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors
Seed Everywhere
VHS_LoadVideo
VHS_SelectImages
VHS_VideoInfo
VHS_VideoCombine
easy positive
easy float
AddLabel
ImageResizeKJ
ImageConcatMulti
AddLabel
ImageResizeKJ
ImageConcatMulti
MiDaS-DepthMapPreprocessor
Scribble_XDoG_Preprocessor
DWPreprocessor
AIO_Preprocessor
MiDaS-DepthMapPreprocessor
Scribble_XDoG_Preprocessor
DWPreprocessor
AIO_Preprocessor
DWPreprocessor
ImageResizeKJ
ImpactMakeImageBatch
CM_NearestSDXLResolution
WanVideoEncode
ImageResize+
RIFE VFI
rife47.pth
FinalFrameSelector
FinalFrameSelector

Create a new video by restyling an existing video with a reference image.

Key Inputs

Load Reference Video: Use any Mp4 that you would like to transform

Image reference: Use any JPG or PNG showing your subject clearly in the style you'd like

Set Video Prompt: as descriptive a prompt as possible.

Width & height: Optimal resolution settings are noted, 1280x720 by default.

Frame load cap: how many desired frames in the output video (for Wan, it must be a multiple of 4, plus 1. for example, 65, or 101)

Skip first frames: Start the AI process somewhere in further into the video's timeline

Select every nth frame: Only process every other Nth frame in the generated video.

Output Path

../outputs/Video2Video_Restyle_Wan/

Workflow

Read more

N