runpod/comfyui/workflows/image-to-video/cogvideox-i2v-production-v1.json

{
  "last_node_id": 8,
  "last_link_id": 10,
  "nodes": [
    {
      "id": 1,
      "type": "LoadImage",
      "pos": [50, 100],
      "size": [315, 314],
      "widgets_values": ["input_frame.png", "image"],
      "title": "API Input Image",
      "flags": {},
      "order": 0,
      "mode": 0,
      "properties": {
        "Node name for S&R": "LoadImage"
      },
      "outputs": [
        {
          "name": "IMAGE",
          "type": "IMAGE",
          "links": [1],
          "slot_index": 0
        },
        {
          "name": "MASK",
          "type": "MASK",
          "links": null
        }
      ]
    },
    {
      "id": 2,
      "type": "DownloadAndLoadCogVideoModel",
      "pos": [50, 500],
      "size": [350, 100],
      "widgets_values": ["THUDM/CogVideoX-5b-I2V", "bf16", "disabled", true],
      "title": "CogVideoX-5b-I2V Loader",
      "flags": {},
      "order": 1,
      "mode": 0,
      "properties": {
        "Node name for S&R": "DownloadAndLoadCogVideoModel"
      },
      "outputs": [
        {
          "name": "model",
          "type": "COGVIDEOMODEL",
          "links": [2],
          "slot_index": 0
        },
        {
          "name": "vae",
          "type": "VAE",
          "links": [3, 10],
          "slot_index": 1
        }
      ]
    },
    {
      "id": 7,
      "type": "CLIPLoader",
      "pos": [50, 650],
      "size": [350, 100],
      "widgets_values": ["t5xxl_fp16.safetensors", "sd3"],
      "title": "T5 CLIP Loader",
      "flags": {},
      "order": 2,
      "mode": 0,
      "properties": {
        "Node name for S&R": "CLIPLoader"
      },
      "outputs": [
        {
          "name": "CLIP",
          "type": "CLIP",
          "links": [4, 5],
          "slot_index": 0
        }
      ]
    },
    {
      "id": 3,
      "type": "CogVideoTextEncode",
      "pos": [450, 100],
      "size": [400, 200],
      "widgets_values": ["Camera movement description, action, scene details", 1, false],
      "title": "API Video Prompt (Positive)",
      "flags": {},
      "order": 3,
      "mode": 0,
      "properties": {
        "Node name for S&R": "CogVideoTextEncode"
      },
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 4
        }
      ],
      "outputs": [
        {
          "name": "conditioning",
          "type": "CONDITIONING",
          "links": [6],
          "slot_index": 0
        },
        {
          "name": "clip",
          "type": "CLIP",
          "links": null
        }
      ]
    },
    {
      "id": 8,
      "type": "CogVideoTextEncode",
      "pos": [450, 350],
      "size": [400, 200],
      "widgets_values": ["low quality, blurry, distorted, watermark", 1, true],
      "title": "API Video Prompt (Negative)",
      "flags": {},
      "order": 4,
      "mode": 0,
      "properties": {
        "Node name for S&R": "CogVideoTextEncode"
      },
      "inputs": [
        {
          "name": "clip",
          "type": "CLIP",
          "link": 5
        }
      ],
      "outputs": [
        {
          "name": "conditioning",
          "type": "CONDITIONING",
          "links": [7],
          "slot_index": 0
        },
        {
          "name": "clip",
          "type": "CLIP",
          "links": null
        }
      ]
    },
    {
      "id": 9,
      "type": "CogVideoImageEncode",
      "pos": [450, 600],
      "size": [315, 100],
      "widgets_values": [],
      "title": "Encode Input Image",
      "flags": {},
      "order": 5,
      "mode": 0,
      "properties": {
        "Node name for S&R": "CogVideoImageEncode"
      },
      "inputs": [
        {
          "name": "vae",
          "type": "VAE",
          "link": 3
        },
        {
          "name": "start_image",
          "type": "IMAGE",
          "link": 1
        }
      ],
      "outputs": [
        {
          "name": "samples",
          "type": "LATENT",
          "links": [8],
          "slot_index": 0
        }
      ]
    },
    {
      "id": 4,
      "type": "CogVideoSampler",
      "pos": [900, 100],
      "size": [315, 474],
      "widgets_values": [49, 50, 6.0, 42, "fixed", "CogVideoXDDIM", 1.0],
      "title": "CogVideoX Sampler (6s @ 8fps)",
      "flags": {},
      "order": 6,
      "mode": 0,
      "properties": {
        "Node name for S&R": "CogVideoSampler"
      },
      "inputs": [
        {
          "name": "model",
          "type": "COGVIDEOMODEL",
          "link": 2
        },
        {
          "name": "positive",
          "type": "CONDITIONING",
          "link": 6
        },
        {
          "name": "negative",
          "type": "CONDITIONING",
          "link": 7
        },
        {
          "name": "image_cond_latents",
          "type": "LATENT",
          "link": 8
        }
      ],
      "outputs": [
        {
          "name": "samples",
          "type": "LATENT",
          "links": [9],
          "slot_index": 0
        }
      ]
    },
    {
      "id": 5,
      "type": "CogVideoDecode",
      "pos": [1250, 100],
      "size": [315, 200],
      "widgets_values": [true, 240, 360, 0.25, 0.25],
      "title": "VAE Decode Video",
      "flags": {},
      "order": 7,
      "mode": 0,
      "properties": {
        "Node name for S&R": "CogVideoDecode"
      },
      "inputs": [
        {
          "name": "vae",
          "type": "VAE",
          "link": 10
        },
        {
          "name": "samples",
          "type": "LATENT",
          "link": 9
        }
      ],
      "outputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "links": [11],
          "slot_index": 0
        }
      ]
    },
    {
      "id": 6,
      "type": "VHS_VideoCombine",
      "pos": [1600, 100],
      "size": [315, 200],
      "widgets_values": [8, 0, "cogvideox_output", "video/h264-mp4", "yuv420p", 19, true, false],
      "title": "Combine Video Frames",
      "flags": {},
      "order": 8,
      "mode": 0,
      "properties": {
        "Node name for S&R": "VHS_VideoCombine"
      },
      "inputs": [
        {
          "name": "images",
          "type": "IMAGE",
          "link": 11
        }
      ],
      "outputs": [
        {
          "name": "Filenames",
          "type": "VHS_FILENAMES",
          "links": null
        }
      ]
    }
  ],
  "links": [
    [1, 1, 0, 9, 1, "IMAGE"],
    [2, 2, 0, 4, 0, "COGVIDEOMODEL"],
    [3, 2, 1, 9, 0, "VAE"],
    [4, 7, 0, 3, 0, "CLIP"],
    [5, 7, 0, 8, 0, "CLIP"],
    [6, 3, 0, 4, 1, "CONDITIONING"],
    [7, 8, 0, 4, 2, "CONDITIONING"],
    [8, 9, 0, 4, 3, "LATENT"],
    [9, 4, 0, 5, 1, "LATENT"],
    [10, 2, 1, 5, 0, "VAE"],
    [11, 5, 0, 6, 0, "IMAGE"]
  ],
  "groups": [],
  "config": {},
  "extra": {
    "workflow_info": {
      "name": "CogVideoX Image-to-Video Production",
      "version": "1.2.0",
      "description": "AI-driven image-to-video using CogVideoX-5b-I2V. Generate 6-second videos (49 frames @ 8fps) from input images with camera movement and action.",
      "category": "image-to-video",
      "tags": ["cogvideox", "i2v", "video-generation", "production"],
      "requirements": {
        "models": ["CogVideoX-5b-I2V", "T5-XXL FP16"],
        "custom_nodes": ["ComfyUI-VideoHelperSuite", "ComfyUI-CogVideoXWrapper"],
        "vram_min": "20GB",
        "vram_recommended": "24GB"
      },
      "parameters": {
        "input_image": {
          "node_id": 1,
          "widget_index": 0,
          "type": "image",
          "required": true,
          "description": "Starting frame for video generation"
        },
        "positive_prompt": {
          "node_id": 3,
          "widget_index": 0,
          "type": "string",
          "required": true,
          "default": "Camera movement description, action, scene details",
          "description": "Describe desired camera movement, actions, and scene"
        },
        "negative_prompt": {
          "node_id": 8,
          "widget_index": 0,
          "type": "string",
          "required": false,
          "default": "low quality, blurry, distorted, watermark",
          "description": "Undesired elements to avoid"
        },
        "num_frames": {
          "node_id": 4,
          "widget_index": 0,
          "type": "integer",
          "required": false,
          "default": 49,
          "min": 1,
          "max": 1024,
          "description": "Number of frames to generate (49 = ~6s @ 8fps)"
        },
        "steps": {
          "node_id": 4,
          "widget_index": 1,
          "type": "integer",
          "required": false,
          "default": 50,
          "min": 20,
          "max": 100,
          "description": "Sampling steps (50 recommended for quality)"
        },
        "cfg": {
          "node_id": 4,
          "widget_index": 2,
          "type": "float",
          "required": false,
          "default": 6.0,
          "min": 1.0,
          "max": 30.0,
          "description": "Classifier-free guidance scale"
        },
        "seed": {
          "node_id": 4,
          "widget_index": 3,
          "type": "integer",
          "required": false,
          "default": 42,
          "description": "Random seed for reproducibility"
        },
        "fps": {
          "node_id": 6,
          "widget_index": 0,
          "type": "integer",
          "required": false,
          "default": 8,
          "description": "Output video framerate"
        }
      },
      "outputs": {
        "video": {
          "node_id": 6,
          "type": "video",
          "format": "MP4 (H.264)",
          "resolution": "Based on input image",
          "duration": "~6 seconds @ 8fps (49 frames)"
        }
      },
      "performance": {
        "avg_generation_time": "120-180 seconds",
        "vram_usage": "~20-22GB",
        "gpu_utilization": "95-100%"
      },
      "use_cases": [
        "Animate static images with camera motion",
        "Create video loops from single frames",
        "Add dynamic movement to product shots",
        "Generate cinematic camera movements"
      ],
      "notes": [
        "CogVideoX-5b-I2V is specifically trained for image-to-video generation",
        "Model will download automatically on first use (~10GB)",
        "Enable VAE tiling to reduce VRAM usage",
        "Higher steps (50-100) improve quality but increase generation time",
        "T5-XXL text encoder required - automatically linked from SD3.5"
      ]
    }
  },
  "version": 0.4
}