ComfyUI Node: Wan 2.2 VACE Fun 14b Video-to-Video (fal)

Authored by gokayfem

Created

Updated

171 stars

Category

FAL/VideoGeneration

Inputs

prompt STRING
video VIDEO
task
  • depth
  • pose
preprocess BOOLEAN
ref_images IMAGE
first_frame IMAGE
last_frame IMAGE
negative_prompt STRING
seed INT
resolution
  • 480p
  • 580p
  • 720p
aspect_ratio
  • auto
  • 16:9
  • 9:16
  • 1:1
num_inference_steps INT
guidance_scale FLOAT
sampler
  • unipc
  • dpm++
  • euler
match_input_num_frames BOOLEAN
num_frames INT
match_input_frames_per_second BOOLEAN
frames_per_second INT
shift INT
acceleration
  • none
  • low
  • regular
video_quality
  • low
  • medium
  • high
video_write_mode
  • balanced
  • fast
  • small
return_frames_zip BOOLEAN
num_interpolated_frames INT
temporal_downsample_factor INT
enable_auto_downsample BOOLEAN
auto_downsample_min_fps INT
interpolator_model
  • rife
  • film
enable_safety_checker BOOLEAN
enable_output_safety_checker BOOLEAN
variations INT

Outputs

STRING

STRING

Extension: ComfyUI-fal-API

Custom nodes for using fal API. Video generation with Kling, Runway, Luma. Image generation with Flux. LLMs and VLMs OpenAI, Claude, Llama and Gemini.

Authored by gokayfem

View Nodes

Run ComfyUI workflows in the Cloud!

No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues

Learn more