LTX-2 姿態轉影片
透過姿態引導產生高品質影片,LTX-2 支援音訊與影片同步產生,姿態控制精準、動作富有表現力、執行高效。
下載工作流程在 Cloud 中試用 API 文件
00:00
工作流程內部
來源範本的唯讀預覽。請在 Cloud 中開啟,以探索節點並進行變更。
從您的程式碼呼叫此模型
以下請求使用與 Playground 相同的已準備節點圖和設定。每次提交都可能啟動付費執行;若提交結果不明,請勿自動重試提交。
1 取得 API 金鑰 ↗
What you need
- Runs on
- Comfy Cloud
- 金鑰
- COMFY_API_KEY
- 您的檔案
- 由程式碼透過其 URL 上傳
需要付費 Cloud 方案與點數。
下載 API JSONAPI 文件 ↗
# 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({
"144": {
"class_type": "GetVideoComponents",
"inputs": {
"video": [
"185",
0
]
},
"_meta": {
"title": "Get Video Components"
}
},
"152": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": 0,
"image": [
"144",
0
],
"length": [
"168",
0
]
},
"_meta": {
"title": "Get Image from Batch"
}
},
"160": {
"class_type": "LoadImage",
"inputs": {
"image": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Load Image"
}
},
"164": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"184",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": [
"167",
0
],
"resize_type.width": [
"166",
0
],
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"165": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"160",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": [
"167",
0
],
"resize_type.width": [
"166",
0
],
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"166": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1280
},
"_meta": {
"title": "Width"
}
},
"167": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Height"
}
},
"168": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 121
},
"_meta": {
"title": "Frame Count"
}
},
"169": {
"class_type": "PrimitiveBoolean",
"inputs": {
"value": False
},
"_meta": {
"title": "Ignore First Frame?"
}
},
"175": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/LTX_2.0",
"format": "auto",
"format.codec": "auto",
"video": [
"143:106",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"184": {
"class_type": "DWPreprocessor",
"inputs": {
"bbox_detector": "yolox_l.onnx",
"detect_body": "enable",
"detect_face": "disable",
"detect_hand": "enable",
"image": [
"152",
0
],
"pose_estimator": "dw-ll_ucoco_384_bs5.torchscript.pt",
"resolution": 512,
"scale_stick_for_xinsr_cn": "disable"
},
"_meta": {
"title": "DWPose Estimator"
}
},
"185": {
"class_type": "LoadVideo",
"inputs": {
"button": {
"clicked": False,
"computedDisabled": False,
"computedHeight": 24,
"label": "choose file to upload",
"last_y": 50,
"name": "upload",
"options": {
"canvasOnly": True,
"serialize": False
},
"type": "button",
"y": 50
},
"file": "UPLOADED_pose_video_FILENAME"
},
"_meta": {
"title": "Load Video"
}
},
"143:100": {
"class_type": "LatentUpscaleModelLoader",
"inputs": {
"model_name": "ltx-2-spatial-upscaler-x2-1.0.safetensors"
},
"_meta": {
"title": "Load Latent Upscale Model"
}
},
"143:101": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"143:122",
1
],
"video_latent": [
"143:151",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"143:103": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2-19b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"143:104": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"143:122",
0
],
"negative": [
"143:132",
1
],
"positive": [
"143:132",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"143:105": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2-19b-distilled-lora-384.safetensors",
"model": [
"143:134",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"143:106": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"143:139",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"143:148",
0
],
"images": [
"143:144",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"143:107": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"143:108",
0
],
"latent_image": [
"143:101",
0
],
"noise": [
"143:143",
0
],
"sampler": [
"143:98",
0
],
"sigmas": [
"143:99",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"143:108": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"143:105",
0
],
"negative": [
"143:104",
1
],
"positive": [
"143:104",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"143:110": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"143:155",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"143:111": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"143:96",
0
],
"batch_size": 1,
"frame_rate": [
"143:145",
0
],
"frames_number": [
"143:110",
2
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"143:112": {
"class_type": "LTXVLatentUpsampler",
"inputs": {
"samples": [
"143:104",
2
],
"upscale_model": [
"143:100",
0
],
"vae": [
"143:103",
2
]
},
"_meta": {
"title": "spatial"
}
},
"143:113": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"143:138",
0
],
"vae": [
"143:103",
2
]
},
"_meta": {
"title": "VAE Decode"
}
},
"143:114": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"143:148",
0
],
"negative": [
"143:119",
0
],
"positive": [
"143:124",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"143:115": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"143:110",
1
],
"length": [
"143:110",
2
],
"width": [
"143:110",
0
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"143:116": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"143:111",
0
],
"video_latent": [
"143:132",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"143:119": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"143:97",
0
],
"text": "blurry, low quality, still frame, frames, watermark, overlay, titles, has blurbox, has subtitles"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"143:122": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"143:123",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"143:123": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"143:93",
0
],
"latent_image": [
"143:116",
0
],
"noise": [
"143:126",
0
],
"sampler": [
"143:94",
0
],
"sigmas": [
"143:95",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"143:124": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"143:97",
0
],
"text": "In a realistic cinematic style, a lone sentinel in heavy obsidian-and-silver plate armour and a frayed charcoal mantle stands on a frozen salt flat at twilight, then begins to dance. Moving slowly and gracefully despite the armour, the sentinel floats both arms up and out to the sides, sweeps one gauntlet across the chest, steps left and right, bends into a gentle lunge, tilts the torso and raises both hands overhead before lowering them in a wave. The mantle swings with each turn and frost dust lifts from the cracked white ground. The camera holds still at full-body distance under a vast, cold overcast sky with a thin glow on the horizon. Sound: the creak and clink of metal plates, boots crunching on salt, and a low, steady wind."
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"143:126": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 0
},
"_meta": {
"title": "RandomNoise"
}
},
"143:132": {
"class_type": "LTXVAddGuide",
"inputs": {
"frame_idx": 0,
"image": [
"164",
0
],
"latent": [
"143:149",
0
],
"negative": [
"143:114",
1
],
"positive": [
"143:114",
0
],
"strength": 1,
"vae": [
"143:103",
2
]
},
"_meta": {
"title": "LTXVAddGuide"
}
},
"143:134": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2-19b-ic-lora-pose-control.safetensors",
"model": [
"143:103",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"143:138": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"143:107",
1
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"143:139": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"143:96",
0
],
"samples": [
"143:138",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"143:143": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 0
},
"_meta": {
"title": "RandomNoise"
}
},
"143:144": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"143:138",
0
],
"temporal_overlap": 8,
"temporal_size": 4096,
"tile_size": 512,
"vae": [
"143:103",
2
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"143:145": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 24
},
"_meta": {
"title": "Int"
}
},
"143:148": {
"class_type": "PrimitiveFloat",
"inputs": {
"value": 24
},
"_meta": {
"title": "Float"
}
},
"143:149": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"169",
0
],
"image": [
"165",
0
],
"latent": [
"143:115",
0
],
"strength": 1,
"vae": [
"143:103",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"143:151": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"169",
0
],
"image": [
"165",
0
],
"latent": [
"143:112",
0
],
"strength": 1,
"vae": [
"143:103",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"143:155": {
"class_type": "ImageScaleBy",
"inputs": {
"image": [
"164",
0
],
"scale_by": 0.5,
"upscale_method": "lanczos"
},
"_meta": {
"title": "Upscale Image By"
}
},
"143:93": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 3,
"model": [
"143:134",
0
],
"negative": [
"143:132",
1
],
"positive": [
"143:132",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"143:94": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"143:95": {
"class_type": "LTXVScheduler",
"inputs": {
"base_shift": 0.95,
"latent": [
"143:116",
0
],
"max_shift": 2.05,
"steps": 20,
"stretch": True,
"terminal": 0.1
},
"_meta": {
"title": "LTXVScheduler"
}
},
"143:96": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2-19b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"143:97": {
"class_type": "LTXAVTextEncoderLoader",
"inputs": {
"ckpt_name": "ltx-2-19b-dev-fp8.safetensors",
"device": "default",
"text_encoder": "gemma_3_12B_it_fp4_mixed.safetensors"
},
"_meta": {
"title": "Load LTXV Audio Text Encoder"
}
},
"143:98": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "gradient_estimation"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"143:99": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "0.909375, 0.725, 0.421875, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
}
})
workflow.set_input("160", "image", client.assets.from_url("https://comfy.org/catalog-media/3be01b31-4698-4186-956d-4f6daa179b8e/1043c6bb-f78c-4bc1-9ebb-49710675437e"))
workflow.set_input("185", "file", client.assets.from_url("https://comfy.org/catalog-media/145a3aa5-a96a-4a02-9110-214f6a0afedd/cb97a2bb-20eb-443d-9bb8-a024127619ca"))
# 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("175"):
output.to_file(output.name)試試範例
關於此工作流程
LTX-2 姿勢轉影片工作流程,專為將姿勢引導轉換為高品質影片內容設計,並支援音訊與影片同步生成。採用 Lightricks 的 LTX-2 模型,提供精確的姿勢控制與豐富動作表現,適合創作動態影片內容。流程整合多個節點,如 GetVideoComponents、PreviewImage 與 SaveVideo,分別負責影片分解、影格預覽與最終輸出。核心特色為 comfyui_controlnet_aux 自訂節點,進一步提升姿勢控制與動作表現的精度。
技術上,流程從 LoadVideo、ResizeImageMaskNode 等節點進行影片與影像預處理,接著用 DWPreprocessor 微調影片設定,確保影格數與解析度最佳化。支援最高 1920x1088 解析度,預設為 720p 以提升效率。影格數需為 8 的倍數加 1,以確保流暢過渡與同步。此流程特別適合需要精細動作與音訊同步的創作者,善用 LTX-2 模型實現專業級成果。
問答
解析度需可被 64 整除。預設為 720p,但若系統支援可用到 1920x1088。
這可確保影片過渡流暢與同步,避免產生雜訊或異常。
雖然流程高效,但是否能即時生成取決於你的系統效能與影片內容複雜度。
請專注於細緻的姿勢引導,並確保解析度與影格數符合流程要求。