LTX-2 포즈 투 비디오
포즈 가이드로 고품질 비디오를 생성하고 LTX-2를 사용하여 동기화된 오디오-비디오 생성을 제공합니다. 정밀한 포즈 제어, 표현력 있는 움직임, 효율적인 성능을 특징으로 합니다.
워크플로 내부
소스 템플릿의 읽기 전용 미리보기입니다. Cloud에서 열어 노드를 살펴보고 변경할 수 있습니다.
코드에서 이 모델 호출하기
아래 요청은 Playground와 동일하게 준비된 그래프와 설정을 사용합니다. 제출할 때마다 유료 실행이 시작될 수 있으므로 결과를 알 수 없는 제출을 자동으로 재시도하지 마세요.
What you need
- Runs on
- Comfy Cloud
- 키
- COMFY_API_KEY
- 내 파일
- 코드가 해당 URL에서 업로드
유료 Cloud 요금제와 크레딧이 필요합니다.
# 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)예시 사용해 보기
이 워크플로 정보
The LTX-2 Pose to Video workflow is designed to transform pose guidance into high-quality video content with synchronized audio and video generation. Utilizing the LTX-2 model from Lightricks, this workflow offers precise control over pose and expressive motion, making it ideal for creating dynamic video content.
The workflow integrates various nodes such as GetVideoComponents, PreviewImage, and SaveVideo, which help in breaking down the video into components, previewing frames, and saving the final output, respectively. A key feature of this workflow is its use of the comfyui_controlnet_aux custom nodes, which enhance the precision of pose control and motion expression.
Technically, the workflow begins with video and image preprocessing using nodes like LoadVideo and ResizeImageMaskNode. It then employs the DWPreprocessor for refining video settings, ensuring optimal frame count and resolution. The workflow is designed to handle resolutions up to 1920x1088, though it defaults to 720p for efficiency. The frame count must be divisible by 8 plus 1, ensuring smooth transitions and synchronization.
This workflow is particularly useful for creators seeking to produce videos with detailed motion and synchronized audio, leveraging the power of the LTX-2 model to achieve professional-grade results.
질문과 답변
The resolution must be divisible by 64. The default is 720p, but you can use up to 1920x1088 if your system supports it.
This ensures smooth transitions and synchronization in the video, preventing any potential artifacts or glitches.
While the workflow is efficient, real-time generation depends on your system's capabilities and the complexity of the video content.
Focus on detailed pose guidance and ensure your video settings, such as resolution and frame count, adhere to the workflow's requirements.
관련 워크플로
- LTX-2
LTX-2 I2V와 LoRA로 모든 것을 압축하세요
- LTX-2, Lightricks
LTX-2 뎁스 투 비디오
- LTX-2, Lightricks
LTX-2 이미지 기반 비디오 생성 (증류)
- LTX-2, Lightricks
LTX-2 캐니 투 비디오
- LTX-2, Lightricks
LTX-2 텍스트 기반 비디오 생성
- LTX-2, Lightricks
LTX-2 텍스트 기반 비디오 생성 (증류)
- LTX-2, Lightricks
LTX-2: Image to Video
- LTX-2
LTX-2: 오디오를 비디오로
- LTX-2, Lightricks
LTX-2: 텍스트에서 비디오로