# 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": [
"50",
2
],
"model": [
"54",
0
],
"negative": [
"50",
1
],
"positive": [
"50",
0
],
"sampler_name": "uni_pc",
"scheduler": "simple",
"seed": 987948718394761,
"steps": 20
},
"_meta": {
"title": "KSampler"
}
},
"6": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"38",
0
],
"text": "The caribou stands on the frozen tundra at winter twilight, slowly lifts its head and turns it toward the camera, its breath streaming out in thick white clouds of vapour. The small bird on its back hops forward, shakes the frost from its feathers and takes off in a short, fluttering loop before landing again. Fine powder snow drifts low across the ground in the wind and the long winter fur ripples along its neck and flanks. The camera slowly circles a quarter turn around the animal while gently pushing in, keeping it centred against the dark mountains. Cold blue light, natural steady motion, photorealistic wildlife footage, shallow depth of field."
},
"_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_i2v_480p_14B_fp16.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"
}
},
"50": {
"class_type": "WanImageToVideo",
"inputs": {
"batch_size": 1,
"clip_vision_output": [
"51",
0
],
"height": 480,
"length": 33,
"negative": [
"7",
0
],
"positive": [
"6",
0
],
"start_image": [
"52",
0
],
"vae": [
"39",
0
],
"width": 832
},
"_meta": {
"title": "WanImageToVideo"
}
},
"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": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Load Image"
}
},
"54": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"37",
0
],
"shift": 8
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"55": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": 16,
"images": [
"8",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"56": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"55",
0
]
},
"_meta": {
"title": "Save Video"
}
}
})
workflow.set_input("52", "image", client.assets.from_url("https://comfy.org/catalog-media/61125d76-ad10-4148-b782-c9969346db7f/20c0f481-14a6-4fbf-8846-01747fff0715"))
# 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("56"):
output.to_file(output.name)