HuMo Video Generation

# 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({
    "6": {
        "class_type": "CLIPTextEncode",
        "inputs": {
            "clip": [
                "38",
                0
            ],
            "text": "A young boy in sci-fi style clothing is talking to the camera in an alien desert."
        },
        "_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": "humo_17B_fp8_e4m3fn.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"
        }
    },
    "48": {
        "class_type": "ModelSamplingSD3",
        "inputs": {
            "model": [
                "61",
                0
            ],
            "shift": 8
        },
        "_meta": {
            "title": "ModelSamplingSD3"
        }
    },
    "49": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "video_humo_reference_image.png"
        },
        "_meta": {
            "title": "Load Image"
        }
    },
    "56": {
        "class_type": "AudioEncoderEncode",
        "inputs": {
            "audio": [
                "58",
                0
            ],
            "audio_encoder": [
                "57",
                0
            ]
        },
        "_meta": {
            "title": "AudioEncoderEncode"
        }
    },
    "57": {
        "class_type": "AudioEncoderLoader",
        "inputs": {
            "audio_encoder_name": "whisper_large_v3_fp16.safetensors"
        },
        "_meta": {
            "title": "Load Audio Encoder"
        }
    },
    "58": {
        "class_type": "LoadAudio",
        "inputs": {
            "audio": "video_humo_input_audio.wav"
        },
        "_meta": {
            "title": "Load Audio"
        }
    },
    "59": {
        "class_type": "SaveVideo",
        "inputs": {
            "filename_prefix": "video/ComfyUI",
            "format": "auto",
            "format.codec": "auto",
            "video": [
                "60",
                0
            ]
        },
        "_meta": {
            "title": "Save Video"
        }
    },
    "60": {
        "class_type": "CreateVideo",
        "inputs": {
            "audio": [
                "58",
                0
            ],
            "bit_depth": "auto",
            "codec": "none",
            "color_space": "sRGB",
            "fps": 25,
            "images": [
                "63",
                0
            ]
        },
        "_meta": {
            "title": "Create Video"
        }
    },
    "61": {
        "class_type": "LoraLoaderModelOnly",
        "inputs": {
            "lora_name": "lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
            "model": [
                "37",
                0
            ],
            "strength_model": 1
        },
        "_meta": {
            "title": "Load LoRA"
        }
    },
    "63": {
        "class_type": "VAEDecode",
        "inputs": {
            "samples": [
                "64",
                0
            ],
            "vae": [
                "39",
                0
            ]
        },
        "_meta": {
            "title": "VAE Decode"
        }
    },
    "64": {
        "class_type": "KSampler",
        "inputs": {
            "cfg": 1,
            "denoise": 1,
            "latent_image": [
                "65",
                2
            ],
            "model": [
                "48",
                0
            ],
            "negative": [
                "65",
                1
            ],
            "positive": [
                "65",
                0
            ],
            "sampler_name": "uni_pc",
            "scheduler": "simple",
            "seed": 1067760026265042,
            "steps": 6
        },
        "_meta": {
            "title": "KSampler"
        }
    },
    "65": {
        "class_type": "WanHuMoImageToVideo",
        "inputs": {
            "audio_encoder_output": [
                "56",
                0
            ],
            "batch_size": 1,
            "height": 640,
            "length": 97,
            "negative": [
                "7",
                0
            ],
            "positive": [
                "6",
                0
            ],
            "ref_image": [
                "49",
                0
            ],
            "vae": [
                "39",
                0
            ],
            "width": 640
        },
        "_meta": {
            "title": "WanHuMoImageToVideo"
        }
    }
})

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)