LTX-2 圖生影片(蒸餾版)
使用LTX-2蒸餾模型將靜態圖像變為動態影片,音訊與影片同步。專為快速產生最佳化,同時保持品質。支援表情嘴型、自然動作,產生速度更快。
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({
"75": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/LTX_2.0_i2v",
"format": "auto",
"format.codec": "auto",
"video": [
"92:97",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"98": {
"class_type": "LoadImage",
"inputs": {
"image": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Load Image"
}
},
"102": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"98",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": 720,
"resize_type.width": 1280,
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"92:1": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2-19b-distilled.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"92:105": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"102",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"92:106": {
"class_type": "ResizeImagesByLongerEdge",
"inputs": {
"images": [
"102",
0
],
"longer_edge": 1536
},
"_meta": {
"title": "Resize Images by Longer Edge (DEPRECATED)"
}
},
"92:107": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": False,
"image": [
"92:99",
0
],
"latent": [
"92:43",
0
],
"strength": 1,
"vae": [
"92:1",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"92:108": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": False,
"image": [
"92:99",
0
],
"latent": [
"92:84",
0
],
"strength": 1,
"vae": [
"92:1",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"92:11": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 10
},
"_meta": {
"title": "RandomNoise"
}
},
"92:112": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"92:3",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"92:113": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "1., 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"92:22": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": 25,
"negative": [
"92:112",
0
],
"positive": [
"92:3",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"92:3": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"92:60",
0
],
"text": "One continuous shot. The enduro rider flies through the air over the black volcanic ridge, the front wheel dipping as the bike comes down, then lands hard on the wet track. The suspension compresses, mud and grit spray out from both tyres, and he leans forward, opens the throttle and rides away along the same ridge toward the low sun breaking through the storm clouds. The camera pans smoothly to follow the bike from the side as it falls and lands, then keeps tracking it in the same setting as it speeds off, with the rain mist and golden light staying constant. Sound of the engine revving hard, the heavy thud of the landing, gravel spraying, wind gusting past the camera and distant thunder over the empty plain."
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"92:41": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"92:47",
0
],
"latent_image": [
"92:56",
0
],
"noise": [
"92:11",
0
],
"sampler": [
"92:8",
0
],
"sigmas": [
"92:113",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"92:43": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"92:91",
1
],
"length": [
"92:62",
0
],
"width": [
"92:91",
0
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"92:47": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"92:1",
0
],
"negative": [
"92:22",
1
],
"positive": [
"92:22",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"92:48": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2-19b-distilled.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"92:51": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"92:48",
0
],
"batch_size": 1,
"frame_rate": 25,
"frames_number": [
"92:62",
0
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"92:56": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"92:51",
0
],
"video_latent": [
"92:107",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"92:60": {
"class_type": "LTXAVTextEncoderLoader",
"inputs": {
"ckpt_name": "ltx-2-19b-distilled.safetensors",
"device": "default",
"text_encoder": "gemma_3_12B_it_fp4_mixed.safetensors"
},
"_meta": {
"title": "Load LTXV Audio Text Encoder"
}
},
"92:62": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 121
},
"_meta": {
"title": "Length"
}
},
"92:66": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "gradient_estimation"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"92:67": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 0
},
"_meta": {
"title": "RandomNoise"
}
},
"92:70": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"92:82",
0
],
"latent_image": [
"92:83",
0
],
"noise": [
"92:67",
0
],
"sampler": [
"92:66",
0
],
"sigmas": [
"92:73",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"92:73": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "0.909375, 0.725, 0.421875, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"92:76": {
"class_type": "LatentUpscaleModelLoader",
"inputs": {
"model_name": "ltx-2-spatial-upscaler-x2-1.0.safetensors"
},
"_meta": {
"title": "Load Latent Upscale Model"
}
},
"92:8": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"92:80": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"92:41",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"92:81": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"92:80",
0
],
"negative": [
"92:22",
1
],
"positive": [
"92:22",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"92:82": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"92:1",
0
],
"negative": [
"92:81",
1
],
"positive": [
"92:81",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"92:83": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"92:80",
1
],
"video_latent": [
"92:108",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"92:84": {
"class_type": "LTXVLatentUpsampler",
"inputs": {
"samples": [
"92:81",
2
],
"upscale_model": [
"92:76",
0
],
"vae": [
"92:1",
2
]
},
"_meta": {
"title": "spatial"
}
},
"92:89": {
"class_type": "EmptyImage",
"inputs": {
"batch_size": 1,
"color": 0,
"height": [
"92:105",
1
],
"width": [
"92:105",
0
]
},
"_meta": {
"title": "Empty Image"
}
},
"92:90": {
"class_type": "ImageScaleBy",
"inputs": {
"image": [
"92:89",
0
],
"scale_by": 0.5,
"upscale_method": "lanczos"
},
"_meta": {
"title": "Upscale Image By"
}
},
"92:91": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"92:90",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"92:94": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"92:70",
1
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"92:95": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"92:94",
0
],
"vae": [
"92:1",
2
]
},
"_meta": {
"title": "VAE Decode"
}
},
"92:96": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"92:48",
0
],
"samples": [
"92:94",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"92:97": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"92:96",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": 25,
"images": [
"92:95",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"92:99": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"92:106",
0
],
"img_compression": 33
},
"_meta": {
"title": "LTXV Preprocess"
}
}
})
workflow.set_input("98", "image", client.assets.from_url("https://comfy.org/catalog-media/9a3b7fb5-dad7-490b-8cd9-50f0b6cbeaed/71bdcc61-f097-4ecf-a8c8-e14fd79c59cc"))
# 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("75"):
output.to_file(output.name)試試範例
關於此工作流程
此 ComfyUI 工作流程使用 Lightricks 的 LTX-2 distilled 模型,將單張靜態圖片轉成動態影片。它把整個動畫流程封裝在一個 Subgraph 節點(b7c2d337-c38d-4c04-922b-2d638449d13e)中,讓你專注在提示詞與參數,而不是手動接線底層元件。來源圖片由 LoadImage 載入,並透過 ResizeImageMaskNode 轉成適合影片的安全尺寸;接著交由 LTX-2 Distilled Subgraph 產生時間上連貫的影格,並提供表情動作與口型同步。輸出影片(以及模型提供時的音訊)會由 SaveVideo 寫入磁碟。畫布中的 MarkdownNote 提供內嵌操作指引與 Subgraph 文件連結,協助你理解並自訂封裝的圖形。
問答
寬度與高度請設為可被 64 整除的數值(例如 1280x768、1920x1088)。影格數請使用 8n+1(例如 9、17、25、33)。若輸入無效值,Subgraph 會自動選擇最接近的有效參數,因此不會顯示錯誤,但結果可能不會與你輸入的數字完全一致。
LTX-2 蒸餾版 Subgraph 在提示詞的音訊區段包含對白時,可能產生表情式口型同步。當模型回傳音軌時,SaveVideo 會把它封裝到輸出中。若你的模型版本/權重不輸出音訊,你會得到無聲影片(可在剪輯軟體中後製加入音訊)。
使用蒸餾模型預設的 720p 以加快執行,提示詞要精準描述隨時間變化的動作,並選擇中等影格數如 17 或 25。若放大到 1920x1088,時間會更長。為了穩定性,迭代時固定 seed,並避免在同一段短片裡塞入過於激烈的動作描述。
此工作流程設計為容錯:會在不提示的情況下把寬/高貼近到最接近的有效值(64 的倍數),並把影格數貼近到 8n+1。執行後請檢查 Subgraph 的實際設定;若你需要特定結果,請把輸入調整到最接近的有效目標。