# 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({
"3": {
"class_type": "KSampler",
"inputs": {
"cfg": 6,
"denoise": 1,
"latent_image": [
"76",
2
],
"model": [
"66",
0
],
"negative": [
"76",
1
],
"positive": [
"76",
0
],
"sampler_name": "uni_pc",
"scheduler": "simple",
"seed": 622093119444720,
"steps": 20
},
"_meta": {
"title": "KSampler"
}
},
"6": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"38",
0
],
"text": "Fashion photography, a inflated man wearing Balenciaga clothes, fashion magazine, Balenciaga style, studio, photographer by Hugo, On-Camera Flash"
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"7": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"38",
0
],
"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"
},
"_meta": {
"title": "CLIP Text Encode (Negative Prompt)"
}
},
"8": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"3",
0
],
"vae": [
"39",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"37": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "wan2.1_fun_inp_1.3B_bf16.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"38": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"device": "default",
"type": "wan"
},
"_meta": {
"title": "Load CLIP"
}
},
"39": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "wan_2.1_vae.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"49": {
"class_type": "CLIPVisionLoader",
"inputs": {
"clip_name": "clip_vision_h.safetensors"
},
"_meta": {
"title": "Load CLIP Vision"
}
},
"51": {
"class_type": "CLIPVisionEncode",
"inputs": {
"clip_vision": [
"49",
0
],
"crop": "none",
"image": [
"52",
0
]
},
"_meta": {
"title": "CLIP Vision Encode"
}
},
"52": {
"class_type": "LoadImage",
"inputs": {
"image": "wan2.1_fun_inp_start_image.png"
},
"_meta": {
"title": "Start_image"
}
},
"65": {
"class_type": "SkipLayerGuidanceDiT",
"inputs": {
"double_layers": "9,10",
"end_percent": 0.8000000000000002,
"model": [
"37",
0
],
"rescaling_scale": 0,
"scale": 3,
"single_layers": "9,10",
"start_percent": 0.01
},
"_meta": {
"title": "SkipLayerGuidanceDiT"
}
},
"66": {
"class_type": "CFGZeroStar",
"inputs": {
"model": [
"68",
0
]
},
"_meta": {
"title": "CFGZeroStar"
}
},
"67": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"65",
0
],
"shift": 5.000000000000001
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"68": {
"class_type": "UNetTemporalAttentionMultiply",
"inputs": {
"cross_structural": 1.2,
"cross_temporal": 1.3,
"model": [
"67",
0
],
"self_structural": 1,
"self_temporal": 1
},
"_meta": {
"title": "UNetTemporalAttentionMultiply"
}
},
"72": {
"class_type": "LoadImage",
"inputs": {
"image": "wan2.1_fun_inp_end_image.png"
},
"_meta": {
"title": "End_image"
}
},
"76": {
"class_type": "WanFunInpaintToVideo",
"inputs": {
"batch_size": 1,
"clip_vision_output": [
"51",
0
],
"end_image": [
"72",
0
],
"height": 768,
"length": 81,
"negative": [
"7",
0
],
"positive": [
"6",
0
],
"start_image": [
"52",
0
],
"vae": [
"39",
0
],
"width": 480
},
"_meta": {
"title": "WanFunInpaintToVideo"
}
},
"79": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": 16,
"images": [
"8",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"80": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"79",
0
]
},
"_meta": {
"title": "Save Video"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)