Nodes/Replicate Select/Wan 2.2 I2V Fast (Replicate)
ComfyUI Node

Wan 2.2 I2V Fast (Replicate)

A ComfyUI node in Replicate Select/video with 15 inputs and 1 output.

By Pharma-Lobby·Created about a month ago·Updated about a month ago· 0
Wan 2.2 I2V Fast (Replicate)
  • image
  • last_image
  • video_path
prompt
num_frames81
resolution480p
frames_per_second16
interpolate_outputfalse
go_fasttrue
sample_shift12.00
seed0
disable_safety_checkerfalse
lora_weights_transformer
lora_scale_transformer1.00
lora_weights_transformer_2
lora_scale_transformer_21.00
CategoryReplicate Select/video

Inputs (15)

NameTypeDefaultDescription
promptSTRINGPrompt for video generation
imageIMAGEInput image to generate video from.
last_imageoptIMAGEOptional last image to condition the video generation. If provided, creates smoother transitions between frames.
num_framesoptINT8181–121Number of video frames. 81 frames give the best results
resolutionoptCOMBO480pResolution of video. 16:9 corresponds to 832x480px, and 9:16 is 480x832px
frames_per_secondoptINT165–30Frames per second. Note that the pricing of this model is based on the video duration at 16 fps
interpolate_outputoptBOOLEANfalseInterpolate the generated video to 30 FPS using ffmpeg
go_fastoptBOOLEANtrueGo fast
sample_shiftoptFLOAT12.001–20Sample shift factor
seedoptINT0-2147483648–2147483647Random seed. Leave blank for random
disable_safety_checkeroptBOOLEANfalseDisable safety checker for generated video.
lora_weights_transformeroptSTRINGLoad LoRA weights for the HIGH transformer. Supports arbitrary .safetensors URLs from the Internet (for example, 'https://huggingface.co/TheRaf7/instagirl-v2/resolve/main/Instagirlv2.0_hinoise.safeten
lora_scale_transformeroptFLOAT1.00-1000000000–1000000000Determines how strongly the transformer LoRA should be applied.
lora_weights_transformer_2optSTRINGLoad LoRA weights for the LOW transformer_2. Supports arbitrary .safetensors URLs from the Internet. Can be different from transformer LoRA. (for example, 'https://huggingface.co/TheRaf7/instagirl-v2/
lora_scale_transformer_2optFLOAT1.00-1000000000–1000000000Determines how strongly the transformer_2 LoRA should be applied.

Outputs (1)

NameTypeDescription
video_pathSTRING