Comfy-agent generate_video_clip

name: generate_video_clip

install
source · Clone the upstream repo
git clone https://github.com/steliosot/comfy-agent
manifest: skills/workflows/video_t2v_i2v_avatar/generate_video_clip/skill.yaml
source content

name: generate_video_clip description: Generate a WAN 2.1 video clip using EmptyHunyuanLatentVideo and VHS_VideoCombine (video/h264-mp4). inputs: prompt: type: string default: cinematic product video clip, smooth camera motion, high detail negative_prompt: type: string default: Overexposure, static, blurred details, low quality, artifacts width: type: integer default: 848 height: type: integer default: 480 length: type: integer default: 25 batch_size: type: integer default: 1 steps: type: integer default: 10 cfg: type: number default: 8 frame_rate: type: integer default: 16 filename_prefix: type: string default: video_clip_h264 outputs: animation: string requirements: models: [] custom_nodes: [] links: [] input_modalities:

  • text_prompt output_modalities:
  • application/json model_families:
  • other node_count: null node_types: [] selection_metadata: family: video_t2v_i2v_avatar resource_profile: unknown complexity_score: null estimated_runtime: depends on runtime parameters and server resources warnings:
  • Hand-authored skill (no embedded workflow.json); metadata is inferred and may be approximate. max_width: null max_height: null max_steps: null