Separate an image into editable layers

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "60": {
        "class_type": "SaveImage",
        "inputs": {
            "filename_prefix": "Qwen-image-layers",
            "images": [
                "83:8",
                0
            ]
        },
        "_meta": {
            "title": "Save Image"
        }
    },
    "74": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "UPLOADED_image_FILENAME"
        },
        "_meta": {
            "title": "Load Image"
        }
    },
    "82": {
        "class_type": "ImageScaleToMaxDimension",
        "inputs": {
            "image": [
                "74",
                0
            ],
            "largest_size": 640,
            "upscale_method": "lanczos"
        },
        "_meta": {
            "title": "Scale Image to Max Dimension"
        }
    },
    "116": {
        "class_type": "PrimitiveStringMultiline",
        "inputs": {
            "value": "A cinematic medium shot of a beautiful young woman with fair skin and a joyful, radiant smile, looking back over her shoulder. She has voluminous, curly auburn hair styled in a loose, windblown updo. She is standing on a rugged, rocky coastline overlooking a sun-drenched ocean. She wears a vintage, long-sleeved, high-collared dress in an off-white, crinkled fabric with delicate smocking on the bodice and a simple brown sash at her waist. In the background, the ocean sparkles brightly under the sun, and a majestic tall ship with full sails is visible in the distance. The scene is illuminated by the warm, golden light of the late afternoon, creating a soft, romantic, and nostalgic atmosphere with a shallow depth of field that keeps the woman in sharp focus."
        },
        "_meta": {
            "title": "Prompt"
        }
    },
    "83:118": {
        "class_type": "EmptyQwenImageLayeredLatentImage",
        "inputs": {
            "batch_size": 1,
            "height": [
                "83:78",
                1
            ],
            "layers": 2,
            "width": [
                "83:78",
                0
            ]
        },
        "_meta": {
            "title": "Empty Qwen Image Layered Latent"
        }
    },
    "83:140": {
        "class_type": "LatentCut",
        "inputs": {
            "amount": 16384,
            "dim": "t",
            "index": 1,
            "samples": [
                "83:3",
                0
            ]
        },
        "_meta": {
            "title": "LatentCut"
        }
    },
    "83:3": {
        "class_type": "KSampler",
        "inputs": {
            "cfg": 2.5,
            "denoise": 1,
            "latent_image": [
                "83:118",
                0
            ],
            "model": [
                "83:66",
                0
            ],
            "negative": [
                "83:70",
                0
            ],
            "positive": [
                "83:69",
                0
            ],
            "sampler_name": "euler",
            "scheduler": "simple",
            "seed": 331728509923362,
            "steps": 20
        },
        "_meta": {
            "title": "KSampler"
        }
    },
    "83:37": {
        "class_type": "UNETLoader",
        "inputs": {
            "unet_name": "qwen_image_layered_bf16.safetensors",
            "weight_dtype": "default"
        },
        "_meta": {
            "title": "Load Diffusion Model"
        }
    },
    "83:38": {
        "class_type": "CLIPLoader",
        "inputs": {
            "clip_name": "qwen_2.5_vl_7b_fp8_scaled.safetensors",
            "device": "default",
            "type": "qwen_image"
        },
        "_meta": {
            "title": "Load CLIP"
        }
    },
    "83:39": {
        "class_type": "VAELoader",
        "inputs": {
            "vae_name": "qwen_image_layered_vae.safetensors"
        },
        "_meta": {
            "title": "Load VAE"
        }
    },
    "83:6": {
        "class_type": "CLIPTextEncode",
        "inputs": {
            "clip": [
                "83:38",
                0
            ],
            "text": [
                "116",
                0
            ]
        },
        "_meta": {
            "title": "CLIP Text Encode (Positive Prompt)"
        }
    },
    "83:66": {
        "class_type": "ModelSamplingAuraFlow",
        "inputs": {
            "model": [
                "83:37",
                0
            ],
            "sampling": "flow",
            "shift": 1
        },
        "_meta": {
            "title": "ModelSamplingAuraFlow"
        }
    },
    "83:69": {
        "class_type": "ReferenceLatent",
        "inputs": {
            "conditioning": [
                "83:6",
                0
            ],
            "latent": [
                "83:71",
                0
            ]
        },
        "_meta": {
            "title": "Set Reference Latent"
        }
    },
    "83:7": {
        "class_type": "CLIPTextEncode",
        "inputs": {
            "clip": [
                "83:38",
                0
            ],
            "text": ""
        },
        "_meta": {
            "title": "CLIP Text Encode (Negative Prompt)"
        }
    },
    "83:70": {
        "class_type": "ReferenceLatent",
        "inputs": {
            "conditioning": [
                "83:7",
                0
            ],
            "latent": [
                "83:71",
                0
            ]
        },
        "_meta": {
            "title": "Set Reference Latent"
        }
    },
    "83:71": {
        "class_type": "VAEEncode",
        "inputs": {
            "pixels": [
                "82",
                0
            ],
            "vae": [
                "83:39",
                0
            ]
        },
        "_meta": {
            "title": "VAE Encode"
        }
    },
    "83:76": {
        "class_type": "LatentCutToBatch",
        "inputs": {
            "dim": "t",
            "samples": [
                "83:140",
                0
            ],
            "slice_size": 1
        },
        "_meta": {
            "title": "LatentCutToBatch"
        }
    },
    "83:78": {
        "class_type": "GetImageSize",
        "inputs": {
            "image": [
                "82",
                0
            ]
        },
        "_meta": {
            "title": "Get Image Size"
        }
    },
    "83:8": {
        "class_type": "VAEDecode",
        "inputs": {
            "samples": [
                "83:76",
                0
            ],
            "vae": [
                "83:39",
                0
            ]
        },
        "_meta": {
            "title": "VAE Decode"
        }
    }
})
workflow.set_input("74", "image", client.assets.from_url("https://cdn.jsdelivr.net/gh/Comfy-Org/workflow_templates@90c71fb78b3726392d010ff62a8e79e92d7296ad/input/coastal_smiling_woman.png"))

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)
for output in job.get_outputs("60"):
    output.to_file(output.name)