# 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({
"19": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/Wan2.2_animate",
"format": "auto",
"format.codec": "auto",
"video": [
"344:357",
0
]
},
"_meta": {
"title": "Final Video"
}
},
"159": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1280
},
"_meta": {
"title": "Width"
}
},
"160": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Height"
}
},
"301": {
"class_type": "VHS_LoadVideo",
"inputs": {
"custom_height": 0,
"custom_width": 0,
"force_rate": 0,
"format": "AnimateDiff",
"frame_load_cap": 0,
"select_every_nth": 1,
"skip_first_frames": 0,
"video": "UPLOADED_video_FILENAME"
},
"_meta": {
"title": "Input Video"
}
},
"314": {
"class_type": "VHS_VideoInfo",
"inputs": {
"video_info": [
"301",
3
]
},
"_meta": {
"title": "Video Info 🎥🅥🅗🅢"
}
},
"346": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": 0,
"image": [
"301",
0
],
"length": 1
},
"_meta": {
"title": "Get Image from Batch"
}
},
"348": {
"class_type": "GeminiNanoBanana2",
"inputs": {
"aspect_ratio": "auto",
"images": [
"346",
0
],
"model": "Nano Banana 2 (Gemini 3.1 Flash Image)",
"prompt": [
"351",
0
],
"resolution": "1K",
"response_modalities": "IMAGE",
"seed": 210658028400692,
"system_prompt": "You are an expert image-generation engine. You must ALWAYS produce an image.\nInterpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.\nIf a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.\nPrioritize generating the visual representation above any text, formatting, or conversational requests.",
"thinking_level": "MINIMAL"
},
"_meta": {
"title": "Nano Banana 2"
}
},
"349": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI",
"images": [
"348",
0
]
},
"_meta": {
"title": "Preview Reference Image"
}
},
"351": {
"class_type": "StringConcatenate",
"inputs": {
"delimiter": "",
"string_a": "retain the composition of this image but turn the character into ",
"string_b": "a woman sculpted entirely from translucent rose quartz veined with brushed copper, wearing the same loose open jacket, cropped top and wide trousers but carved from thin, glowing pink crystal with fine copper filigree along every seam and hem, her skin smooth polished quartz with soft light passing through it, her long hair formed from flowing strands of fine copper wire that swing and catch the sun, small copper rings on her fingers, crystal shoes, keeping her joyful expression, her pose, the cracked dry lakebed and the clear blue sky exactly as they are, photorealistic material detail with crisp reflections and light glowing inside the stone"
},
"_meta": {
"title": "Concatenate Text"
}
},
"344:1": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"344:2",
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)"
}
},
"344:18": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
"model": [
"344:20",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"344:2": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"device": "default",
"type": "wan"
},
"_meta": {
"title": "Load CLIP"
}
},
"344:20": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "Wan2_2-Animate-14B_fp8_e4m3fn_scaled_KJ.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"344:21": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"344:2",
0
],
"text": "the person is dancing"
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"344:3": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "wan_2.1_vae.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"344:324": {
"class_type": "DownloadAndLoadSAM2Model",
"inputs": {
"device": "cuda",
"model": "sam2.1_hiera_base_plus.safetensors",
"precision": "fp16",
"segmentor": "video"
},
"_meta": {
"title": "(Down)Load SAM2Model"
}
},
"344:325": {
"class_type": "BlockifyMask",
"inputs": {
"block_size": 32,
"device": "cpu",
"masks": [
"344:327",
0
]
},
"_meta": {
"title": "Blockify Mask"
}
},
"344:326": {
"class_type": "Sam2Segmentation",
"inputs": {
"bboxes": [
"344:334",
3
],
"image": [
"344:337",
0
],
"individual_objects": False,
"keep_model_loaded": False,
"sam2_model": [
"344:324",
0
]
},
"_meta": {
"title": "Sam2Segmentation"
}
},
"344:327": {
"class_type": "GrowMaskWithBlur",
"inputs": {
"blur_radius": 0,
"decay_factor": 1,
"expand": 10,
"fill_holes": False,
"flip_input": False,
"incremental_expandrate": 0,
"lerp_alpha": 1,
"mask": [
"344:326",
0
],
"tapered_corners": True
},
"_meta": {
"title": "Grow Mask With Blur"
}
},
"344:328": {
"class_type": "OnnxDetectionModelLoader",
"inputs": {
"onnx_device": "CUDAExecutionProvider",
"vitpose_model": "vitpose-l-wholebody.onnx",
"yolo_model": "yolov10m.onnx"
},
"_meta": {
"title": "ONNX Detection Model Loader"
}
},
"344:332": {
"class_type": "DrawMaskOnImage",
"inputs": {
"color": "0, 0, 0",
"device": "cpu",
"image": [
"344:338",
0
],
"mask": [
"344:325",
0
]
},
"_meta": {
"title": "Draw Mask On Image"
}
},
"344:334": {
"class_type": "PoseAndFaceDetection",
"inputs": {
"face_padding": 0,
"height": [
"344:337",
2
],
"images": [
"344:337",
0
],
"model": [
"344:328",
0
],
"width": [
"344:337",
1
]
},
"_meta": {
"title": "Pose and Face Detection"
}
},
"344:335": {
"class_type": "DrawViTPose",
"inputs": {
"body_stick_width": -1,
"draw_head": True,
"hand_stick_width": -1,
"height": [
"344:337",
2
],
"pose_data": [
"344:334",
0
],
"retarget_padding": 16,
"width": [
"344:337",
1
]
},
"_meta": {
"title": "Draw ViT Pose"
}
},
"344:337": {
"class_type": "GetImageSizeAndCount",
"inputs": {
"image": [
"344:338",
0
]
},
"_meta": {
"title": "Get Image Size & Count"
}
},
"344:338": {
"class_type": "ImageScale",
"inputs": {
"crop": "center",
"height": [
"160",
0
],
"image": [
"301",
0
],
"upscale_method": "lanczos",
"width": [
"159",
0
]
},
"_meta": {
"title": "Resize Input Video"
}
},
"344:342": {
"class_type": "ImageScale",
"inputs": {
"crop": "center",
"height": [
"160",
0
],
"image": [
"348",
0
],
"upscale_method": "lanczos",
"width": [
"159",
0
]
},
"_meta": {
"title": "Resize Reference Image"
}
},
"344:353": {
"class_type": "TrimVideoLatent",
"inputs": {
"samples": [
"344:355",
0
],
"trim_amount": [
"344:356",
3
]
},
"_meta": {
"title": "Trim Video Latent"
}
},
"344:354": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"344:353",
0
],
"vae": [
"344:3",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"344:355": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"344:356",
2
],
"model": [
"344:60",
0
],
"negative": [
"344:356",
1
],
"positive": [
"344:356",
0
],
"sampler_name": "euler",
"scheduler": "simple",
"seed": 777171427287516,
"steps": 6
},
"_meta": {
"title": "KSampler"
}
},
"344:356": {
"class_type": "WanAnimateToVideo",
"inputs": {
"batch_size": 1,
"clip_vision_output": [
"344:9",
0
],
"continue_motion_max_frames": 5,
"face_video": [
"344:334",
1
],
"height": [
"160",
0
],
"length": [
"301",
1
],
"negative": [
"344:1",
0
],
"pose_video": [
"344:335",
0
],
"positive": [
"344:21",
0
],
"reference_image": [
"344:342",
0
],
"vae": [
"344:3",
0
],
"video_frame_offset": 0,
"width": [
"159",
0
]
},
"_meta": {
"title": "WanAnimateToVideo"
}
},
"344:357": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"301",
2
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"314",
0
],
"images": [
"344:358",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"344:358": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": [
"344:356",
4
],
"image": [
"344:354",
0
],
"length": 4096
},
"_meta": {
"title": "Get Image from Batch"
}
},
"344:4": {
"class_type": "CLIPVisionLoader",
"inputs": {
"clip_name": "clip_vision_h.safetensors"
},
"_meta": {
"title": "Load CLIP Vision"
}
},
"344:60": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"344:99",
0
],
"shift": 8
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"344:9": {
"class_type": "CLIPVisionEncode",
"inputs": {
"clip_vision": [
"344:4",
0
],
"crop": "none",
"image": [
"344:342",
0
]
},
"_meta": {
"title": "CLIP Vision Encode"
}
},
"344:99": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "WanAnimate_relight_lora_fp16.safetensors",
"model": [
"344:18",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
}
})
workflow.set_input("301", "video", client.assets.from_url("https://comfy.org/catalog-media/eba278c1-1bb9-45c4-92c8-f62e649e5b44/4f4b49a9-d6b0-42d4-82a9-f405a7f309d8"))
# 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("19"):
output.to_file(output.name)
for output in job.get_outputs("349"):
output.to_file(output.name)