LTX-2 من العمق إلى فيديو
أنشئ فيديو عالي الجودة من خرائط العمق باستخدام LTX-2؛ مزامنة الصوت والصورة، تحكم دقيق في العمق وإدراك مكاني.
حول
تم تصميم سير عمل LTX-2 من العمق إلى فيديو في ComfyUI لتحويل خرائط العمق إلى فيديوهات عالية الجودة مع دمج توليد صوت/فيديو متزامن. يعتمد سير العمل على نموذج LTX-2 المعروف بالتحكم الدقيق في العمق والإدراك المكاني لإنتاج محتوى فيديو مقنع بصريًا. يبدأ سير العمل بعُقَد مثل 'LoadImage' و'LoadVideo' لاستيراد ملفات الوسائط اللازمة. تُعد عقدة 'GetVideoComponents' أساسية لأنها تستخرج المكونات المهمة من الفيديو، ثم تُعالج عبر عُقَد مثل 'ImageScaleBy' و'ResizeImageMaskNode' لضمان الأبعاد ونِسَب العرض إلى الارتفاع الصحيحة. تُنهي عقدة 'SaveVideo' العملية عبر تجميع الإطارات المعالجة في ملف فيديو. يناسب هذا سير العمل المبدعين الذين يريدون إدخال تأثيرات بصرية قائمة على العمق في مشاريع الفيديو مع أداء فعّال ومخرجات عالية الجودة.
ما تقدّمه
- جارٍ قراءة سير العمل
يعمل في ComfyUI. لا يمكن تشغيل سير العمل هذا على هذه الصفحة. افتحه في Comfy Cloud مع تحميل كل شيء، أو نزّله لاستخدامه في ComfyUI الخاص بك.
جرّبه في Cloudداخل سير العمل
معاينة للقراءة فقط لرسم العقد البياني. افتحه في Comfy Cloud أو نزّله لتعديل العقد.
Loading the graph
Open full-size workflow previewالملفات في سير العمل هذا
- المؤلف
- ComfyUI
يتطلب عُقدًا مخصصة
- جارٍ قراءة سير العمل
استخدم سير العمل هذا من خلال التعليمات البرمجية
يتم إنشاؤه من مخطط سير العمل والمدخلات عندما يكون ذلك ممكنًا؛ وإلا فتُعرض الأمثلة المخزنة. راجع بيانات الاعتماد ونقاط النهاية قبل تشغيل التعليمات البرمجية، إذ قد تترتب عليها رسوم.
What you need
- Runs on
- Comfy Cloud
- المفتاح
- COMFY_API_KEY
يتطلب خطة Cloud مدفوعة ورصيدًا.
# 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": [
"183",
0
]
},
"_meta": {
"title": "Get Video Components"
}
},
"146": {
"class_type": "ImageScaleBy",
"inputs": {
"image": [
"164",
0
],
"scale_by": 0.5,
"upscale_method": "lanczos"
},
"_meta": {
"title": "Upscale Image By"
}
},
"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": "minimalist_sky_view_lounge.png"
},
"_meta": {
"title": "Load Image"
}
},
"164": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"152",
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"
}
},
"183": {
"class_type": "LoadVideo",
"inputs": {
"file": "minimalist_sky_view_lounge.mp4"
},
"_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": [
"181:22",
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": "A wide shot reveals a whimsical outdoor scene with a decorative tree-like structure crafted from brown branches. Golden spherical ornaments and delicate white artificial flowers adorn the branches, catching bright daylight. A small grey and white squirrel stands on a round, light-colored wooden platform at the base, its bushy tail slightly raised. The squirrel dips its head down, nibbling at something on the platform. The camera slowly pushes in, focusing on the squirrel's gentle movements. Soft forest sounds fill the air—rustling leaves, distant birdsong, and a gentle breeze. The golden ornaments shimmer in the sunlight as the squirrel continues to eat."
},
"_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": [
"181:22",
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-depth-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"
}
},
"143:93": {
"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"
}
},
"181:10": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "lotus-depth-d-v1-1.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"181:14": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "vae-ft-mse-840000-ema-pruned.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"181:16": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"181:19",
0
],
"latent_image": [
"181:23",
0
],
"noise": [
"181:18",
0
],
"sampler": [
"181:21",
0
],
"sigmas": [
"181:28",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"181:18": {
"class_type": "DisableNoise",
"inputs": {},
"_meta": {
"title": "DisableNoise"
}
},
"181:19": {
"class_type": "BasicGuider",
"inputs": {
"conditioning": [
"181:68",
0
],
"model": [
"181:10",
0
]
},
"_meta": {
"title": "Basic Guider"
}
},
"181:20": {
"class_type": "BasicScheduler",
"inputs": {
"denoise": 1,
"model": [
"181:10",
0
],
"scheduler": "normal",
"steps": 1
},
"_meta": {
"title": "BasicScheduler"
}
},
"181:21": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"181:22": {
"class_type": "ImageInvert",
"inputs": {
"image": [
"181:8",
0
]
},
"_meta": {
"title": "Invert Image Colors"
}
},
"181:23": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"146",
0
],
"vae": [
"181:14",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"181:28": {
"class_type": "SetFirstSigma",
"inputs": {
"sigma": 999.0000000000002,
"sigmas": [
"181:20",
0
]
},
"_meta": {
"title": "SetFirstSigma"
}
},
"181:68": {
"class_type": "LotusConditioning",
"inputs": {},
"_meta": {
"title": "LotusConditioning"
}
},
"181:8": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"181:16",
0
],
"vae": [
"181:14",
0
]
},
"_meta": {
"title": "VAE Decode"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)الأسئلة والأجوبة
سيقوم سير العمل بضبطها تلقائيًا إلى أقرب قيم صالحة لضمان معالجة سلسة بدون أخطاء.
نعم، يمكنك تجربة دقة 1920x1088 إذا كان جهازك يدعم ذلك، مع التأكد أن الإعدادات قابلة للقسمة على 64.
نعم، تم تصميم سير العمل للتعامل مع توليد صوت/فيديو متزامن لتحسين جودة الناتج.
يستخدم سير العمل نموذج LTX-2 من Lightricks، المعروف بقدرات التحكم بالعمق والإدراك المكاني.