# Run with:
#   fastvideo generate --config scripts/inference/inference_wan_i2v.yaml
generator:
  model_path: Wan-AI/Wan2.1-I2V-14B-480P-Diffusers
  engine:
    num_gpus: 2
    parallelism:
      tp_size: 2
      sp_size: 2
    offload:
      dit: true
      vae: true
      text_encoder: true
      image_encoder: true
      pin_cpu_memory: true
  pipeline:
    workload_type: i2v
    experimental:
      flow_shift: 3.0
request:
  prompt: >-
    An astronaut hatching from an egg, on the surface of the moon, the
    darkness and depth of space realised in the background. High quality,
    ultrarealistic detail and breath-taking movie-like camera shot.
  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: https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg
  sampling:
    seed: 1024
    num_frames: 77
    height: 480
    width: 832
    fps: 16
    num_inference_steps: 40
    guidance_scale: 5.0
  output:
    output_path: outputs_i2v/