{
  "job": "follow",
  "want": "pose",
  "rank": 1,
  "short": "its pose",
  "title": {
    "zh": "照着姿势画",
    "en": "Follow a pose"
  },
  "about": {
    "zh": "读出参考图的姿势，照着这个姿势画。",
    "en": "Reads a picture's pose and draws to it."
  },
  "source": {
    "zh": "参考工作流的「底图控制网」组",
    "en": "The reference workflow's ControlNet group"
  },
  "packs": {
    "DWPreprocessor": "comfyui_controlnet_aux"
  },
  "takes": "reference",
  "control": "pose",
  "nodes": {
    "reference": {
      "class_type": "LoadImage",
      "inputs": {
        "image": "$image"
      }
    },
    "pose": {
      "class_type": "DWPreprocessor",
      "inputs": {
        "image": [
          "reference",
          0
        ],
        "detect_hand": "enable",
        "detect_body": "enable",
        "detect_face": "enable",
        "resolution": 1024,
        "bbox_detector": "yolox_l.torchscript.pt",
        "pose_estimator": "dw-ll_ucoco_384_bs5.torchscript.pt",
        "scale_stick_for_xinsr_cn": "disable"
      }
    },
    "controlnet": {
      "class_type": "ControlNetLoader",
      "inputs": {
        "control_net_name": "$controlnet"
      }
    },
    "steer": {
      "class_type": "ControlNetApplyAdvanced",
      "inputs": {
        "positive": [
          "$sampler.positive",
          "*"
        ],
        "negative": [
          "$sampler.negative",
          "*"
        ],
        "control_net": [
          "controlnet",
          0
        ],
        "image": [
          "pose",
          0
        ],
        "vae": [
          "$decode.vae",
          "*"
        ],
        "strength": 0.8,
        "start_percent": 0.0,
        "end_percent": 0.8
      },
      "wire_to": "$sampler"
    },
    "look": {
      "class_type": "PreviewImage",
      "inputs": {
        "images": [
          "pose",
          0
        ]
      }
    }
  },
  "after": "run_workflow: the picture now takes that pose (strength 0.8, for the first 80% of the steps; lower either for a looser pose). The prompt still says who and what: change it if it fights the pose. Its pose skeleton is among the run's previews: if it is empty or wrong (a crowded or very stylised picture), try control_depth.",
  "variants": {
    "anima": {
      "packs": {
        "DWPreprocessor": "comfyui_controlnet_aux",
        "AnimaLLLiteApply_sdscripts": "ComfyUI-Anima-LLLite"
      },
      "control": null,
      "lllite": "pose",
      "nodes": {
        "reference": {
          "class_type": "LoadImage",
          "inputs": {
            "image": "$image"
          }
        },
        "pose": {
          "class_type": "DWPreprocessor",
          "inputs": {
            "image": [
              "reference",
              0
            ],
            "detect_hand": "enable",
            "detect_body": "enable",
            "detect_face": "enable",
            "resolution": 1024,
            "bbox_detector": "yolox_l.torchscript.pt",
            "pose_estimator": "dw-ll_ucoco_384_bs5.torchscript.pt",
            "scale_stick_for_xinsr_cn": "disable"
          }
        },
        "steer": {
          "class_type": "AnimaLLLiteApply_sdscripts",
          "inputs": {
            "model": [
              "$sampler.model",
              "*"
            ],
            "lllite_name": "$lllite",
            "image": [
              "pose",
              0
            ],
            "strength": 1.0,
            "start_percent": 0.0,
            "end_percent": 1.0,
            "preserve_wrapper": true
          },
          "wire_to": "$sampler"
        },
        "look": {
          "class_type": "PreviewImage",
          "inputs": {
            "images": [
              "pose",
              0
            ]
          }
        }
      },
      "after": "On this Anima model an Anima ControlNet-LLLite steers it, more gently than an SDXL ControlNet: say in the prompt what the picture shows (how many people, what they do), or the prompt wins. Strength 1.0 for all the steps; up to 1.5 holds it closer. run_workflow. Its pose skeleton is among the run's previews: if it is empty or wrong (a crowded or very stylised picture), try control_depth."
    }
  },
  "models": [
    "noob_openpose",
    "thibauld_openpose_sdxl",
    "union_promax_sdxl",
    "anima_lllite_pose"
  ],
  "tested": {
    "gpu": "RTX 4050 Laptop",
    "vram_gb": 6,
    "date": "2026-10-27",
    "runs": [
      {
        "model": "SDXL (Illustrious)",
        "size": "832×1216",
        "seconds": 64
      }
    ]
  }
}