ComfyUI Node

Wan Adaptive Flow

Creates adaptive multi-pass video generation with improved transitions

By fblissjr·Created about a year ago·Updated about a year ago· 5
Wan Adaptive Flow
  • text_embeds
  • model
  • clip_vision
  • vae
  • image_embeds
  • t5_encoder
  • text_embeds
  • bridge_info
analysis_points3
first_pass_steps8
bridge_modeAutomatic
bridge_count1
bridge_strength0.75
lighting_weight0.80
content_weight0.70
composition_weight0.60
save_first_passtrue
original_prompts
CategoryWanSeamlessFlow

Inputs (16)

NameTypeDefaultDescription
text_embedsWANVIDEOTEXTEMBEDS
analysis_pointsINT31–10Number of points to analyze per transition
first_pass_stepsINT81–30Number of steps for initial generation pass
bridge_modeCOMBOAutomaticType of bridge prompt to create
bridge_countINT11–5Number of bridge prompts per transition
bridge_strengthFLOAT0.750.1–1How strongly to apply bridge modifications
modeloptWANVIDEOMODELWanVideo model for initial pass
clip_visionoptCLIP_VISIONCLIP Vision for frame analysis
vaeoptWANVAEVAE for decoding latents
image_embedsoptWANVIDIMAGE_EMBEDSImage embeddings for initial pass
t5_encoderoptWANTEXTENCODERT5 encoder for bridge prompts
lighting_weightoptFLOAT0.800–1
content_weightoptFLOAT0.700–1
composition_weightoptFLOAT0.600–1
save_first_passoptBOOLEANtrue
original_promptsoptSTRINGOriginal prompts separated by |

Outputs (2)

NameTypeDescription
text_embedsWANVIDEOTEXTEMBEDS
bridge_infoSTRING