LTX 2.3 - Lipdub LoRA + Voice Clone
上傳一段 driving 影片並輸入想要的對白,即可使用 LTX 2.3 生成你的影片 lipdub。接著工作流程會用 Chatterbox 將配音音訊轉回原角色的聲線。這是一個完全開源的工作流程,用於替換 driving 影片中角色的說話內容。
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。
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。
# 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({
"5046": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "output_ltx",
"format": "auto",
"format.codec": "auto",
"video": [
"5049:4849",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"5047": {
"class_type": "LoadVideo",
"inputs": {
"file": "UPLOADED_video_FILENAME"
},
"_meta": {
"title": "Load Video"
}
},
"5048": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "A lean East Asian man in his late forties with swept-back black hair touched with silver at the temples stands on a rainy shopping street, rimless sunglasses pushed up on his head, wearing a loose grey overshirt over a blue button-down shirt. He holds a small silver flip phone at chest height, looks straight into the camera with a dry, amused half smile and raised eyebrows, and speaks in a calm, low, slightly amused voice in English, saying: \"Found it in a drawer last night. Twenty years old, and it still rings.\" Pedestrians with clear umbrellas pass softly out of focus behind him, wet pavement reflects the shop lights, steady camera, natural head and hand movement."
},
"_meta": {
"title": "Prompt"
}
},
"5050": {
"class_type": "GetVideoComponents",
"inputs": {
"video": [
"5047",
0
]
},
"_meta": {
"title": "Get Video Components"
}
},
"5051": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "{DIALOGUE}",
"replace": [
"5052",
0
],
"string": [
"5048",
0
]
},
"_meta": {
"title": "Create Prompt"
}
},
"5052": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "Lipdub workflow is now live on Comfy Hub."
},
"_meta": {
"title": "Dialogue"
}
},
"5053": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"5055",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"5050",
2
],
"images": [
"5049:4995",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"5054": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "output_ltx_chatterbox",
"format": "auto",
"format.codec": "auto",
"video": [
"5053",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"5055": {
"class_type": "FL_ChatterboxVC",
"inputs": {
"input_audio": [
"5049:4848",
0
],
"keep_model_loaded": True,
"seed": 12345,
"target_voice": [
"5050",
1
],
"use_cpu": False
},
"_meta": {
"title": "FL Chatterbox VC"
}
},
"5049:1241": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"5049:5010",
2
],
"negative": [
"5049:2612",
0
],
"positive": [
"5049:2483",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"5049:2483": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"5049:4982",
0
],
"text": [
"5051",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"5049:2612": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"5049:4982",
0
],
"text": "pc game, console game, video game, cartoon, childish, ugly"
},
"_meta": {
"title": "CLIP Text Encode (Negative Prompt)"
}
},
"5049:3059": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"5049:5023",
2
],
"length": [
"5049:5025",
1
],
"width": [
"5049:5023",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"5049:3980": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"5049:4010",
0
],
"batch_size": 1,
"frame_rate": [
"5049:5000",
0
],
"frames_number": [
"5049:5025",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"5049:4010": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"5049:4528": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"5049:3980",
0
],
"video_latent": [
"5049:5004",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"5049:4828": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"5049:5102",
0
],
"negative": [
"5049:5006",
1
],
"positive": [
"5049:5006",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"5049:4829": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"5049:4828",
0
],
"latent_image": [
"5049:4528",
0
],
"noise": [
"5049:4832",
0
],
"sampler": [
"5049:4831",
0
],
"sigmas": [
"5049:4984",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"5049:4831": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"5049:4832": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 1
},
"_meta": {
"title": "RandomNoise"
}
},
"5049:4845": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"5049:4829",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"5049:4848": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"5049:4010",
0
],
"samples": [
"5049:4973",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"5049:4849": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"5049:4848",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"5049:5010",
2
],
"images": [
"5049:4995",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"5049:4964": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"5049:5102",
0
],
"negative": [
"5049:5014",
1
],
"positive": [
"5049:5014",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"5049:4967": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 222
},
"_meta": {
"title": "RandomNoise"
}
},
"5049:4969": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"5049:5013",
2
],
"video_latent": [
"5049:5014",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"5049:4971": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"5049:4964",
0
],
"latent_image": [
"5049:4969",
0
],
"noise": [
"5049:4967",
0
],
"sampler": [
"5049:4976",
0
],
"sigmas": [
"5049:4985",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"5049:4973": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"5049:4971",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"5049:4974": {
"class_type": "LatentUpscaleModelLoader",
"inputs": {
"model_name": "ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
},
"_meta": {
"title": "Load Latent Upscale Model"
}
},
"5049:4975": {
"class_type": "LTXVLatentUpsampler",
"inputs": {
"samples": [
"5049:5011",
2
],
"upscale_model": [
"5049:4974",
0
],
"vae": [
"5049:5017",
2
]
},
"_meta": {
"title": "LTXVLatentUpsampler"
}
},
"5049:4976": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"5049:4982": {
"class_type": "LTXAVTextEncoderLoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev.safetensors",
"device": "default",
"text_encoder": "gemma_3_12B_it_fp4_mixed.safetensors"
},
"_meta": {
"title": "Load LTXV Audio Text Encoder"
}
},
"5049:4984": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "1.0, 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"5049:4985": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "0.909375, 0.725, 0.421875, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"5049:4995": {
"class_type": "LTXVTiledVAEDecode",
"inputs": {
"horizontal_tiles": 2,
"last_frame_fix": False,
"latents": [
"5049:5015",
2
],
"overlap": 6,
"vae": [
"5049:5017",
2
],
"vertical_tiles": 2,
"working_device": "auto",
"working_dtype": "auto"
},
"_meta": {
"title": "🅛🅣🅧 LTXV Tiled VAE Decode"
}
},
"5049:5000": {
"class_type": "LTXFloatToInt",
"inputs": {
"a": [
"5049:5010",
2
]
},
"_meta": {
"title": "🅛🅣🅧 Float To Int"
}
},
"5049:5003": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"5049:5010",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "disabled",
"resize_type.height": [
"5049:5101",
1
],
"resize_type.width": [
"5049:5100",
1
],
"scale_method": "area"
},
"_meta": {
"title": "Resize Image/Mask (s2 size)"
}
},
"5049:5004": {
"class_type": "LTXAddVideoICLoRAGuide",
"inputs": {
"crop": "disabled",
"frame_idx": 0,
"image": [
"5049:5009",
0
],
"latent": [
"5049:3059",
0
],
"latent_downscale_factor": 1,
"negative": [
"5049:1241",
1
],
"positive": [
"5049:1241",
0
],
"strength": 1,
"tile_frames": 97,
"tile_overlap": 64,
"tile_size": 256,
"use_streaming": False,
"use_tiled_encode": True,
"vae": [
"5049:5017",
2
]
},
"_meta": {
"title": "🅛🅣🅧 Add Video IC-LoRA Guide"
}
},
"5049:5005": {
"class_type": "LTXVAudioVAEEncode",
"inputs": {
"audio": [
"5049:5010",
1
],
"audio_vae": [
"5049:4010",
0
]
},
"_meta": {
"title": "LTXV Audio VAE Encode"
}
},
"5049:5006": {
"class_type": "LTXVSetAudioRefTokens",
"inputs": {
"audio_latent": [
"5049:5005",
0
],
"negative": [
"5049:5004",
1
],
"positive": [
"5049:5004",
0
]
},
"_meta": {
"title": "🅛🅣🅧 Set Audio Ref Tokens"
}
},
"5049:5009": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"5049:5010",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "disabled",
"resize_type.height": 544,
"resize_type.width": 960,
"scale_method": "area"
},
"_meta": {
"title": "Resize Image/Mask (s1 size)"
}
},
"5049:5010": {
"class_type": "GetVideoComponents",
"inputs": {
"video": [
"5047",
0
]
},
"_meta": {
"title": "Get Video Components"
}
},
"5049:5011": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"5049:4845",
0
],
"negative": [
"5049:5004",
1
],
"positive": [
"5049:5004",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"5049:5013": {
"class_type": "LTXVSetAudioRefTokens",
"inputs": {
"audio_latent": [
"5049:4845",
1
],
"negative": [
"5049:5011",
1
],
"positive": [
"5049:5011",
0
]
},
"_meta": {
"title": "🅛🅣🅧 Set Audio Ref Tokens"
}
},
"5049:5014": {
"class_type": "LTXAddVideoICLoRAGuide",
"inputs": {
"crop": "disabled",
"frame_idx": 0,
"image": [
"5049:5003",
0
],
"latent": [
"5049:4975",
0
],
"latent_downscale_factor": 1,
"negative": [
"5049:5013",
1
],
"positive": [
"5049:5013",
0
],
"strength": 1,
"tile_frames": 97,
"tile_overlap": 64,
"tile_size": 256,
"use_streaming": False,
"use_tiled_encode": True,
"vae": [
"5049:5017",
2
]
},
"_meta": {
"title": "🅛🅣🅧 Add Video IC-LoRA Guide"
}
},
"5049:5015": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"5049:4973",
0
],
"negative": [
"5049:5014",
1
],
"positive": [
"5049:5014",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"5049:5017": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"5049:5018": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2.3-22b-distilled-lora-384-1.1.safetensors",
"model": [
"5049:5017",
0
],
"strength_model": 0.5
},
"_meta": {
"title": "Load LoRA"
}
},
"5049:5023": {
"class_type": "GetImageSizeAndCount",
"inputs": {
"image": [
"5049:5009",
0
]
},
"_meta": {
"title": "Get Image Size & Count"
}
},
"5049:5025": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "(int((a - 1) / 8)) * 8 + 1",
"values.a": [
"5049:5023",
3
]
},
"_meta": {
"title": "Math Expression"
}
},
"5049:5091": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": 960,
"resize_type.width": 544,
"scale_method": "area"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"5049:5096": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": 544,
"length": 121,
"width": 960
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"5049:5100": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a * 2",
"values.a": [
"5049:5023",
1
]
},
"_meta": {
"title": "Upscaled Width"
}
},
"5049:5101": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a * 2",
"values.a": [
"5049:5023",
2
]
},
"_meta": {
"title": "Upscaled Height"
}
},
"5049:5102": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2.3-22b-ic-lora-lipdub-0.9.safetensors",
"model": [
"5049:5018",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
}
})
workflow.set_input("5047", "file", client.assets.from_url("https://comfy.org/catalog-media/8ec5c8bc-e1b1-4b48-8f57-cf50721ff00c/4d895a2f-b562-4898-8318-e65cdacbe834"))
# 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("5054"):
output.to_file(output.name)
for output in job.get_outputs("5046"):
output.to_file(output.name)試試範例
關於此工作流程
此工作流程以 LTX 2.3 與 Chatterbox 聲音轉換為核心,建立完整、開源的 lip-dub 管線。你需要提供一段人物說話的「driving」影片,以及希望他說出的對白。LoadVideo 讀入影片,GetVideoComponents 擷取影格、FPS 與原始音訊。你輸入的對白會從 PrimitiveStringMultiline 提示詞經 RegexReplace 清理標點與空白後,送入 LTX 2.3 Lipdub 節點(自訂節點 ID:1e1eaad5-a949-4d3e-9a68-694e64a936a0)。該節點會在 LTX 2.3 上套用 Lipdub LoRA 微調,讓口型依你的腳本重新對時,同時盡量保留主體身分、頭部動作與場景脈絡。
音訊部分,同一段對白會先生成臨時配音軌,再送入 FL_ChatterboxVC。Chatterbox VC 會以原影片音訊(由 GetVideoComponents 取得)作為聲音參考,將配音重塑為接近說話者的音色與聲學特徵。最後,CreateVideo 以來源 FPS 組合編輯後影格與克隆音訊,SaveVideo 輸出最終唇形同步影片。請注意 MarkdownNote 的尺寸規則:輸入寬 × 高要設為目標輸出的一半(例如輸入 960×544,輸出約為 1920×1088)。
問答
本流程預期輸入寬高為目標輸出的一半,詳見 MarkdownNote。例:960×544 輸入會產生約 1920×1088 輸出。請設定輸入時將目標解析度除以二。
FL_ChatterboxVC 以原影片音訊(來自 GetVideoComponents)作為聲音參考,將產生的配音轉換為目標講者的音色與風格,讓嘴型對齊腳本,同時聲音仍像螢幕上的人物。
請先調整文字:用標點(逗號/句號)加入或移除短暫停頓,保持句子簡潔,避免過長。確保 CreateVideo FPS 與來源一致。清晰、正面且嘴唇無遮擋的畫面也有助於對齊。
建議用短至中長度、光線穩定且嘴部清晰的片段。Chatterbox 參考音訊以乾淨語音(少音樂/雜訊)最佳。如原音軌雜訊多,可裁切乾淨片段或先行降噪。