LTX-2.3: نص إلى فيديو
توليد فيديو من موجه نصي، مع إمكانية استخدام صورة كمرجع. احصل على فيديو عالي الجودة مع حركة وصوت وتفاصيل محسنة، محسّن للتنسيقات العمودية أو الأفقية.
داخل سير العمل
معاينة للقراءة فقط للقالب المصدر. افتحه في Cloud لاستكشاف العُقد وإجراء التغييرات.
Loading the graph
Open full-size workflow previewاستدعِ هذا النموذج من التعليمة البرمجية الخاصة بك
يستخدم الطلب أدناه المخطط والإعدادات المُعدّة نفسها كما في Playground. يمكن لكل إرسال أن يبدأ تشغيلًا مدفوعًا؛ لا تُعِد تلقائيًا محاولة إرسال لا تُعرف نتيجته.
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({
"75": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/LTX_2.3_t2v",
"format": "auto",
"format.codec": "auto",
"video": [
"267:242",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"269": {
"class_type": "LoadImage",
"inputs": {
"image": "example.png"
},
"_meta": {
"title": "Load Image"
}
},
"267:201": {
"class_type": "PrimitiveBoolean",
"inputs": {
"value": True
},
"_meta": {
"title": "Switch to Text to Video?"
}
},
"267:209": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_ancestral_cfg_pp"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"267:211": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "0.85, 0.7250, 0.4219, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"267:212": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"267:217",
0
],
"negative": [
"267:239",
1
],
"positive": [
"267:239",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"267:213": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"267:232",
0
],
"negative": [
"267:212",
1
],
"positive": [
"267:212",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"267:214": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"267:221",
0
],
"batch_size": 1,
"frame_rate": [
"267:261",
1
],
"frames_number": [
"267:225",
0
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"267:215": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"267:231",
0
],
"latent_image": [
"267:222",
0
],
"noise": [
"267:237",
0
],
"sampler": [
"267:209",
0
],
"sigmas": [
"267:252",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"267:216": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"267:217": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"267:215",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"267:218": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"267:219",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"267:219": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"267:213",
0
],
"latent_image": [
"267:229",
0
],
"noise": [
"267:216",
0
],
"sampler": [
"267:246",
0
],
"sigmas": [
"267:211",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"267:220": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"267:221",
0
],
"samples": [
"267:218",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"267:221": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"267:222": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"267:214",
0
],
"video_latent": [
"267:249",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"267:225": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 121
},
"_meta": {
"title": "Length"
}
},
"267:228": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"267:259",
1
],
"length": [
"267:225",
0
],
"width": [
"267:256",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"267:229": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"267:217",
1
],
"video_latent": [
"267:230",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"267:230": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"267:201",
0
],
"image": [
"267:248",
0
],
"latent": [
"267:253",
0
],
"strength": 1,
"vae": [
"267:236",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"267:231": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"267:232",
0
],
"negative": [
"267:239",
1
],
"positive": [
"267:239",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"267:232": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2.3-22b-distilled-lora-384.safetensors",
"model": [
"267:236",
0
],
"strength_model": 0.5
},
"_meta": {
"title": "Load LoRA"
}
},
"267:233": {
"class_type": "LatentUpscaleModelLoader",
"inputs": {
"model_name": "ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
},
"_meta": {
"title": "Load Latent Upscale Model"
}
},
"267:235": {
"class_type": "ResizeImagesByLongerEdge",
"inputs": {
"images": [
"267:238",
0
],
"longer_edge": 1536
},
"_meta": {
"title": "Resize Images by Longer Edge (DEPRECATED)"
}
},
"267:236": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"267:237": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 731987174230470
},
"_meta": {
"title": "RandomNoise"
}
},
"267:238": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"269",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": [
"267:258",
0
],
"resize_type.width": [
"267:257",
0
],
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"267:239": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"267:261",
0
],
"negative": [
"267:247",
0
],
"positive": [
"267:240",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"267:240": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"267:243",
0
],
"text": [
"267:274",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"267:242": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"267:220",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"267:261",
0
],
"images": [
"267:251",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"267:243": {
"class_type": "LTXAVTextEncoderLoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors",
"device": "default",
"text_encoder": "gemma_3_12B_it_fp4_mixed.safetensors"
},
"_meta": {
"title": "Load LTXV Audio Text Encoder"
}
},
"267:246": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_cfg_pp"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"267:247": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"267:272",
1
],
"text": "pc game, console game, video game, cartoon, childish, ugly"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"267:248": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"267:235",
0
],
"img_compression": 18
},
"_meta": {
"title": "LTXV Preprocess"
}
},
"267:249": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"267:201",
0
],
"image": [
"267:248",
0
],
"latent": [
"267:228",
0
],
"strength": 0.7,
"vae": [
"267:236",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"267:251": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"267:218",
0
],
"temporal_overlap": 4,
"temporal_size": 4096,
"tile_size": 768,
"vae": [
"267:236",
2
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"267:252": {
"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"
}
},
"267:253": {
"class_type": "LTXVLatentUpsampler",
"inputs": {
"samples": [
"267:217",
0
],
"upscale_model": [
"267:233",
0
],
"vae": [
"267:236",
2
]
},
"_meta": {
"title": "LTXVLatentUpsampler"
}
},
"267:256": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"267:257",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"267:257": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1280
},
"_meta": {
"title": "Width"
}
},
"267:258": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Height"
}
},
"267:259": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"267:258",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"267:260": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 25
},
"_meta": {
"title": "Frame Rate"
}
},
"267:261": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a",
"values.a": [
"267:260",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"267:266": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "At stormy dusk, a solitary medieval warrior clad in hammered iron plate and sodden chainmail stands atop an expansive, muddy ridge. He wears an open-faced, rounded steel helmet revealing a weathered, scarred face streaked with grime. Sheets of heavy rain cut diagonally through the air, catching the fiery amber glow of a setting sun trapped beneath bruised violet storm clouds. Over five seconds, gale-force winds violently whip his frayed crimson cloak while tempestuous clouds churn rapidly overhead. The warrior slowly shifts his weight, gripping a notched steel longsword. The camera executes a low, continuous arc around his waist before smoothly pushing into a dramatic close-up of his steely, rain-soaked gaze. Ambient audio carries the violent drumming of downpour against steel plate, howling wind, and the distinct, wet creak of shifting leather armor."
},
"_meta": {
"title": "Prompt"
}
},
"267:272": {
"class_type": "LoraLoader",
"inputs": {
"clip": [
"267:243",
0
],
"lora_name": "gemma-3-12b-it-abliterated_lora_rank64_bf16.safetensors",
"model": [
"267:236",
0
],
"strength_clip": 1,
"strength_model": 1
},
"_meta": {
"title": "Load LoRA (Model and CLIP)"
}
},
"267:274": {
"class_type": "TextGenerateLTX2Prompt",
"inputs": {
"clip": [
"267:272",
1
],
"max_length": 256,
"mtp": "auto",
"prompt": [
"267:266",
0
],
"sampling_mode": "on",
"sampling_mode.min_p": 0.05,
"sampling_mode.repetition_penalty": 1.05,
"sampling_mode.seed": 0,
"sampling_mode.temperature": 0.7,
"sampling_mode.top_k": 64,
"sampling_mode.top_p": 0.95,
"thinking": False,
"use_default_template": True
},
"_meta": {
"title": "Generate LTX2 Prompt"
}
},
"267:275": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"267:274",
0
]
},
"_meta": {
"title": "Preview as Text"
}
}
})
# 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)جرّب مثالًا
حول سير العمل هذا
تم تصميم سير العمل LTX-2.3: Text to Video في ComfyUI لتحويل مطالبة نصية إلى فيديو ديناميكي، مع خيار استخدام صورة كمرجع. يستفيد هذا سير العمل من نموذج LTX-2.3 الذي طورته Lightricks، والمُحسّن لتوليد فيديوهات عالية الجودة مع تحسين الحركة والصوت والتفاصيل. يُعد سير العمل فعالًا خصوصًا لإنشاء فيديوهات بصيغتي العمودي والأفقي، ما يجعله مناسبًا لتطبيقات متعددة.
تقنيًا، يدمج سير العمل عدة عُقد أساسية، بما في ذلك عقدة SaveVideo لإخراج الفيديو النهائي، وعقدة LoadImage لإضافة صور مرجعية. تُستخدم عقدة MarkdownNote لتوفير توثيق وإرشادات داخل سير العمل. يتمثل جوهر العملية في العقدة b94257db-cdc1-45d3-8913-ca61e782d9c1 المسؤولة عن تفسير المطالبة النصية وتوليد محتوى الفيديو المقابل. يفيد هذا سير العمل المستخدمين الذين يريدون إنتاج فيديوهات بسرعة انطلاقًا من أوصاف نصية، مع إمكانية تنقيح الإخراج باستخدام صور مرجعية.
الأسئلة والأجوبة
نعم، رفع صورة مطلوب لتوفير مرجع بصري وتحسين التفاصيل في الفيديو الناتج.
نعم، سير العمل مُحسَّن لكلا النمطين، ويمكنك الاختيار حسب احتياجك.
يستخدم سير العمل نموذج LTX-2.3 الذي طوّرته Lightricks، وهو متاح على Huggingface.
يمكنك التحسين عبر ضبط الطلب النصي ليكون أكثر دقة ورفع صور مرجعية مختلفة للتأثير على التفاصيل البصرية.