# 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": [
"105",
0
],
"denoise": 1,
"latent_image": [
"93",
2
],
"model": [
"54",
0
],
"negative": [
"93",
1
],
"positive": [
"93",
0
],
"sampler_name": "uni_pc",
"scheduler": "simple",
"seed": 20,
"steps": [
"103",
0
]
},
"_meta": {
"title": "KSampler"
}
},
"6": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"38",
0
],
"text": "A woman in a dark charcoal high-collar jacket sits in a softly lit broadcast studio and speaks warmly into the black condenser microphone in front of her, like a late-night radio host greeting her listeners. She talks naturally and calmly, her lips moving clearly with every word, with small nods, gentle eyebrow raises and a faint smile on the friendly lines. Her head tilts slightly as she leans a little closer to the microphone, then settles back. Her eyes stay on the camera, blinking naturally. Her hands rest out of frame below the microphone, and nothing passes in front of her face. The camera is locked off at chest height in a single continuous shot. Behind her, cyan and amber edge lights glow on the concrete and the hexagonal acoustic panels, and small indicator lights blink on the equipment racks."
},
"_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)"
}
},
"37": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "wan2.2_s2v_14B_fp8_scaled.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"
}
},
"52": {
"class_type": "LoadImage",
"inputs": {
"image": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Load Image"
}
},
"54": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"107",
0
],
"shift": 8
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"56": {
"class_type": "AudioEncoderEncode",
"inputs": {
"audio": [
"58",
0
],
"audio_encoder": [
"57",
0
]
},
"_meta": {
"title": "AudioEncoderEncode"
}
},
"57": {
"class_type": "AudioEncoderLoader",
"inputs": {
"audio_encoder_name": "wav2vec2_large_english_fp16.safetensors"
},
"_meta": {
"title": "Load Audio Encoder"
}
},
"58": {
"class_type": "LoadAudio",
"inputs": {
"audio": "UPLOADED_audio_FILENAME"
},
"_meta": {
"title": "Load Audio"
}
},
"80": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"95",
0
],
"vae": [
"39",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"82": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"58",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": 16,
"images": [
"96",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"93": {
"class_type": "WanSoundImageToVideo",
"inputs": {
"audio_encoder_output": [
"56",
0
],
"batch_size": 1,
"height": 480,
"length": [
"104",
0
],
"negative": [
"7",
0
],
"positive": [
"6",
0
],
"ref_image": [
"52",
0
],
"vae": [
"39",
0
],
"width": 832
},
"_meta": {
"title": "WanSoundImageToVideo"
}
},
"94": {
"class_type": "LatentCut",
"inputs": {
"amount": 1,
"dim": "t",
"index": 0,
"samples": [
"85:78",
0
]
},
"_meta": {
"title": "LatentCut"
}
},
"95": {
"class_type": "LatentConcat",
"inputs": {
"dim": "t",
"samples1": [
"94",
0
],
"samples2": [
"85:78",
0
]
},
"_meta": {
"title": "LatentConcat"
}
},
"96": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": [
"100",
0
],
"image": [
"80",
0
],
"length": 4096
},
"_meta": {
"title": "Get Image from Batch"
}
},
"100": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 3
},
"_meta": {
"title": "Batch sizes"
}
},
"103": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 4
},
"_meta": {
"title": "Steps"
}
},
"104": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 77
},
"_meta": {
"title": "Chunk Length"
}
},
"105": {
"class_type": "PrimitiveFloat",
"inputs": {
"value": 1
},
"_meta": {
"title": "CFG"
}
},
"107": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors",
"model": [
"37",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"113": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"82",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"79:76": {
"class_type": "WanSoundImageToVideoExtend",
"inputs": {
"audio_encoder_output": [
"56",
0
],
"length": [
"104",
0
],
"negative": [
"7",
0
],
"positive": [
"6",
0
],
"ref_image": [
"52",
0
],
"vae": [
"39",
0
],
"video_latent": [
"3",
0
]
},
"_meta": {
"title": "WanSoundImageToVideoExtend"
}
},
"79:77": {
"class_type": "KSampler",
"inputs": {
"cfg": [
"105",
0
],
"denoise": 1,
"latent_image": [
"79:76",
2
],
"model": [
"54",
0
],
"negative": [
"79:76",
1
],
"positive": [
"79:76",
0
],
"sampler_name": "uni_pc",
"scheduler": "simple",
"seed": 1,
"steps": [
"103",
0
]
},
"_meta": {
"title": "KSampler"
}
},
"79:78": {
"class_type": "LatentConcat",
"inputs": {
"dim": "t",
"samples1": [
"3",
0
],
"samples2": [
"79:77",
0
]
},
"_meta": {
"title": "LatentConcat"
}
},
"85:76": {
"class_type": "WanSoundImageToVideoExtend",
"inputs": {
"audio_encoder_output": [
"56",
0
],
"length": [
"104",
0
],
"negative": [
"7",
0
],
"positive": [
"6",
0
],
"ref_image": [
"52",
0
],
"vae": [
"39",
0
],
"video_latent": [
"79:78",
0
]
},
"_meta": {
"title": "WanSoundImageToVideoExtend"
}
},
"85:77": {
"class_type": "KSampler",
"inputs": {
"cfg": [
"105",
0
],
"denoise": 1,
"latent_image": [
"85:76",
2
],
"model": [
"54",
0
],
"negative": [
"85:76",
1
],
"positive": [
"85:76",
0
],
"sampler_name": "uni_pc",
"scheduler": "simple",
"seed": 250,
"steps": [
"103",
0
]
},
"_meta": {
"title": "KSampler"
}
},
"85:78": {
"class_type": "LatentConcat",
"inputs": {
"dim": "t",
"samples1": [
"79:78",
0
],
"samples2": [
"85:77",
0
]
},
"_meta": {
"title": "LatentConcat"
}
}
})
workflow.set_input("58", "audio", client.assets.from_url("https://comfy.org/catalog-media/3bb9ee36-53c7-459b-8344-8c127597fd3c/1b849bac-2e14-43ef-8edd-ea2859d20a09"))
workflow.set_input("52", "image", client.assets.from_url("https://comfy.org/catalog-media/6e2796d5-1dfd-42f2-b918-b7157f9c5067/2d1cb5de-3ee8-4dfc-97c5-bc7d189528cd"))
# 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("113"):
output.to_file(output.name)