# Run with:
#   fastvideo generate --config scripts/inference/inference_longcat_i2v.yaml
generator:
  model_path: FastVideo/LongCat-Video-I2V-Diffusers
  engine:
    num_gpus: 1
    parallelism:
      tp_size: 1
      sp_size: 1
    offload:
      dit: false
      pin_cpu_memory: false
  pipeline:
    workload_type: i2v
    experimental:
      enable_bsa: false
request:
  prompt: >-
    A woman sits at a wooden table by the window in a cozy café. She reaches
    out with her right hand, picks up the white coffee cup from the saucer,
    and gently brings it to her lips to take a sip. After drinking, she places
    the cup back on the table and looks out the window, enjoying the peaceful
    atmosphere.
  negative_prompt: >-
    Bright tones, overexposed, static, blurred details, subtitles, style,
    works, paintings, images, static, overall gray, worst quality, low
    quality, JPEG compression residue, ugly, incomplete, extra fingers,
    poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen
    limbs, fused fingers, still picture, messy background, three legs, many
    people in the background, walking backwards
  inputs:
    image_path: assets/girl.png
  sampling:
    seed: 42
    num_frames: 93
    height: 480
    width: 480
    fps: 15
    num_inference_steps: 50
    guidance_scale: 4.0
  output:
    output_path: outputs_video/longcat_i2v