ComfyUI/benchmarks/workflows/wan22_i2v.json

{
  "97": {
    "inputs": {"image": "__INPUT_IMAGE__"},
    "class_type": "LoadImage",
    "_meta": {"title": "Start Frame Image"}
  },
  "108": {
    "inputs": {
      "filename_prefix": "video/Wan2.2_image_to_video",
      "format": "auto",
      "codec": "auto",
      "video-preview": "",
      "video": ["130:117", 0]
    },
    "class_type": "SaveVideo",
    "_meta": {"title": "Save Video"}
  },
  "130:105": {
    "inputs": {
      "clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
      "type": "wan",
      "device": "default"
    },
    "class_type": "CLIPLoader",
    "_meta": {"title": "Load CLIP"}
  },
  "130:106": {
    "inputs": {"vae_name": "wan_2.1_vae.safetensors"},
    "class_type": "VAELoader",
    "_meta": {"title": "Load VAE"}
  },
  "130:107": {
    "inputs": {
      "text": "A felt-style little eagle cashier greeting, waving, and smiling at the camera.",
      "clip": ["130:105", 0]
    },
    "class_type": "CLIPTextEncode",
    "_meta": {"title": "CLIP Text Encode (Positive Prompt)"}
  },
  "130:109": {
    "inputs": {"shift": 5.000000000000001, "model": ["130:126", 0]},
    "class_type": "ModelSamplingSD3",
    "_meta": {"title": "ModelSamplingSD3"}
  },
  "130:110": {
    "inputs": {
      "add_noise": "enable",
      "noise_seed": 636787045983965,
      "steps": 4,
      "cfg": 1,
      "sampler_name": "euler",
      "scheduler": "simple",
      "start_at_step": 0,
      "end_at_step": 2,
      "return_with_leftover_noise": "enable",
      "model": ["130:109", 0],
      "positive": ["130:128", 0],
      "negative": ["130:128", 1],
      "latent_image": ["130:128", 2]
    },
    "class_type": "KSamplerAdvanced",
    "_meta": {"title": "KSampler (Advanced)"}
  },
  "130:111": {
    "inputs": {
      "add_noise": "disable",
      "noise_seed": 0,
      "steps": 4,
      "cfg": 1,
      "sampler_name": "euler",
      "scheduler": "simple",
      "start_at_step": 2,
      "end_at_step": 4,
      "return_with_leftover_noise": "disable",
      "model": ["130:124", 0],
      "positive": ["130:128", 0],
      "negative": ["130:128", 1],
      "latent_image": ["130:110", 0]
    },
    "class_type": "KSamplerAdvanced",
    "_meta": {"title": "KSampler (Advanced)"}
  },
  "130:117": {
    "inputs": {"fps": 16, "images": ["130:129", 0]},
    "class_type": "CreateVideo",
    "_meta": {"title": "Create Video"}
  },
  "130:122": {
    "inputs": {
      "unet_name": "wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors",
      "weight_dtype": "default"
    },
    "class_type": "UNETLoader",
    "_meta": {"title": "Load Diffusion Model"}
  },
  "130:123": {
    "inputs": {
      "unet_name": "wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors",
      "weight_dtype": "default"
    },
    "class_type": "UNETLoader",
    "_meta": {"title": "Load Diffusion Model"}
  },
  "130:124": {
    "inputs": {"shift": 5.000000000000001, "model": ["130:127", 0]},
    "class_type": "ModelSamplingSD3",
    "_meta": {"title": "ModelSamplingSD3"}
  },
  "130:125": {
    "inputs": {
      "text": "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",
      "clip": ["130:105", 0]
    },
    "class_type": "CLIPTextEncode",
    "_meta": {"title": "CLIP Text Encode (Negative Prompt)"}
  },
  "130:126": {
    "inputs": {
      "lora_name": "wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors",
      "strength_model": 1.0000000000000002,
      "model": ["130:122", 0]
    },
    "class_type": "LoraLoaderModelOnly",
    "_meta": {"title": "Load LoRA"}
  },
  "130:127": {
    "inputs": {
      "lora_name": "wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors",
      "strength_model": 1.0000000000000002,
      "model": ["130:123", 0]
    },
    "class_type": "LoraLoaderModelOnly",
    "_meta": {"title": "Load LoRA"}
  },
  "130:128": {
    "inputs": {
      "width": 720,
      "height": 720,
      "length": 81,
      "batch_size": 1,
      "positive": ["130:107", 0],
      "negative": ["130:125", 0],
      "vae": ["130:106", 0],
      "start_image": ["97", 0]
    },
    "class_type": "WanImageToVideo",
    "_meta": {"title": "WanImageToVideo"}
  },
  "130:129": {
    "inputs": {"samples": ["130:111", 0], "vae": ["130:106", 0]},
    "class_type": "VAEDecode",
    "_meta": {"title": "VAE Decode"}
  }
}