LTX-2: Audio a video
Sube un archivo de audio y un fotograma de imagen inicial. Genera un vídeo sincronizado con el audio utilizando el modelo LTX-2.
Acerca de
El flujo de trabajo LTX-2: Audio a Vídeo está diseñado para transformar un archivo de audio y un fotograma de imagen inicial en un vídeo sincronizado. Este proceso aprovecha el modelo LTX-2, conocido por su capacidad de interpretar señales de audio y traducirlas en contenido visual dinámico. El flujo de trabajo comienza con los Nodos 'LoadImage' y 'LoadAudio', que permiten a los usuarios introducir la imagen inicial y el archivo de audio que servirán como base para la generación de vídeo. Estas Entradas se procesan luego mediante una serie de Nodos personalizados, incluyendo 'comfyui-kjnodes', que son cruciales para mantener la sincronización entre los elementos de audio y vídeo.
A nivel técnico, el flujo de trabajo utiliza un Nodo único identificado por el ID '3458504c-2bd1-4267-8722-6f2478115b42', que desempeña un papel clave al alinear el ritmo y el tempo del audio con las transiciones visuales. El Nodo 'SaveVideo' es el paso final, convirtiendo los datos procesados en un archivo de vídeo. Este flujo de trabajo es especialmente útil para creadores que buscan producir contenido de vídeo atractivo a partir de pistas de audio, como videoclips o piezas de arte audiovisual. Su carácter experimental significa que los resultados pueden variar, ofreciendo una oportunidad particular para la exploración creativa.
Lo que proporcionas
- Leyendo el flujo de trabajo
Se ejecuta en ComfyUI. Este flujo de trabajo no puede ejecutarse en esta página. Ábrelo en Comfy Cloud con todo cargado o descárgalo para tu propio ComfyUI.
Probar en CloudAún no hay resultados de muestra para este flujo de trabajo.
Dentro del flujo de trabajo
Una vista previa de solo lectura del gráfico de nodos. Ábrelo en Comfy Cloud o descárgalo para editar los nodos.
Loading the graph
Open full-size workflow previewArchivos de este flujo de trabajo
- Autor
- ComfyUI
Requiere nodos personalizados
- Leyendo el flujo de trabajo
Usa este flujo de trabajo desde código
Se genera a partir del gráfico y las entradas del flujo de trabajo cuando es posible; de lo contrario, se muestran ejemplos almacenados. Revisa las credenciales y los endpoints antes de ejecutar el código, ya que puede generar cargos.
What you need
- Runs on
- Comfy Cloud
- Clave
- COMFY_API_KEY
Requiere un plan de pago de Cloud y créditos.
# 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({
"444": {
"class_type": "LoadImage",
"inputs": {
"image": "ltx2-a2v-input.png"
},
"_meta": {
"title": "Load Image"
}
},
"565": {
"class_type": "LoadAudio",
"inputs": {
"audio": "ltx2-a2v-input.mp3"
},
"_meta": {
"title": "Load Audio"
}
},
"982": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ltx-2-a2v",
"format": "auto",
"format.codec": "auto",
"video": [
"994:995",
0
]
},
"_meta": {
"title": "Final Video"
}
},
"984": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ltx-2-a2v",
"format": "auto",
"format.codec": "auto",
"video": [
"994:983",
0
]
},
"_meta": {
"title": "Preview Video"
}
},
"994:1001": {
"class_type": "PrimitiveFloat",
"inputs": {
"value": 24
},
"_meta": {
"title": "FPS"
}
},
"994:819": {
"class_type": "LTXVChunkFeedForward",
"inputs": {
"chunks": 4,
"dim_threshold": 4096,
"model": [
"994:952",
0
]
},
"_meta": {
"title": "LTXV Chunk FeedForward"
}
},
"994:820": {
"class_type": "LTX2_NAG",
"inputs": {
"inplace": True,
"model": [
"994:819",
0
],
"nag_alpha": 0.25,
"nag_cond_video": [
"994:922",
0
],
"nag_scale": 11,
"nag_tau": 2.5
},
"_meta": {
"title": "LTX2 NAG"
}
},
"994:821": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"994:923",
0
],
"img_compression": 25
},
"_meta": {
"title": "LTXV Preprocess"
}
},
"994:842": {
"class_type": "LTXVImgToVideoInplaceKJ",
"inputs": {
"latent": [
"994:855",
0
],
"num_images": "1",
"num_images.image_1": [
"994:821",
0
],
"num_images.index_1": 0,
"num_images.strength_1": 1,
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "LTXVImgToVideoInplaceKJ"
}
},
"994:855": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"994:923",
2
],
"length": 241,
"width": [
"994:923",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"994:857": {
"class_type": "FloatConstant",
"inputs": {
"value": 10.25
},
"_meta": {
"title": "window_size_seconds"
}
},
"994:890": {
"class_type": "AudioSeparation",
"inputs": {
"audio": [
"994:892",
0
],
"chunk_fade_shape": "linear",
"chunk_length": 10,
"chunk_overlap": 0.1
},
"_meta": {
"title": "AudioSeparation"
}
},
"994:892": {
"class_type": "AudioCrop",
"inputs": {
"audio": [
"565",
0
],
"end_time": "2:05",
"start_time": "1:05"
},
"_meta": {
"title": "AudioCrop"
}
},
"994:895": {
"class_type": "VAELoaderKJ",
"inputs": {
"device": "main_device",
"vae_name": "LTX2_audio_vae_bf16.safetensors",
"weight_dtype": "bf16"
},
"_meta": {
"title": "VAELoader KJ"
}
},
"994:904": {
"class_type": "VAELoaderKJ",
"inputs": {
"device": "main_device",
"vae_name": "LTX2_video_vae_bf16.safetensors",
"weight_dtype": "bf16"
},
"_meta": {
"title": "VAELoader KJ"
}
},
"994:921": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"994:951",
0
],
"text": "the man is singing passionately"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"994:922": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"994:951",
0
],
"text": "still image with no motion, subtitles, text, scene change"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"994:923": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 2,
"height": 720,
"image": [
"444",
0
],
"keep_proportion": "crop",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": 720
},
"_meta": {
"title": "Resize Image v2"
}
},
"994:927": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"994:1001",
0
],
"negative": [
"994:950",
0
],
"positive": [
"994:921",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"994:933": {
"class_type": "LTX2SamplingPreviewOverride",
"inputs": {
"model": [
"994:820",
0
],
"preview_rate": 8
},
"_meta": {
"title": "LTX2 Sampling Preview Override"
}
},
"994:950": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"994:921",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"994:951": {
"class_type": "DualCLIPLoader",
"inputs": {
"clip_name1": "gemma_3_12B_it_fp8_scaled.safetensors",
"clip_name2": "ltx-2-19b-embeddings_connector_distill_bf16.safetensors",
"device": "default",
"type": "ltxv"
},
"_meta": {
"title": "Load CLIP (Dual)"
}
},
"994:952": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "ltx-2-19b-distilled_transformer_only_bf16.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"994:969:823": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"994:969:824": {
"class_type": "LTXVAudioVAEEncode",
"inputs": {
"audio": [
"994:969:862",
0
],
"audio_vae": [
"994:895",
0
]
},
"_meta": {
"title": "LTXV Audio VAE Encode"
}
},
"994:969:827": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"994:969:830",
0
],
"latent_image": [
"994:969:829",
0
],
"noise": [
"994:969:823",
0
],
"sampler": [
"994:969:953",
0
],
"sigmas": [
"994:969:954",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"994:969:829": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"994:969:859",
1
],
"video_latent": [
"994:969:896",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"994:969:830": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"994:933",
0
],
"negative": [
"994:969:896",
1
],
"positive": [
"994:969:896",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"994:969:831": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"994:969:827",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"994:969:832": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"994:969:831",
0
],
"negative": [
"994:969:896",
1
],
"positive": [
"994:969:896",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"994:969:843": {
"class_type": "GetImageRangeFromBatch",
"inputs": {
"images": [
"994:978:826",
0
],
"num_frames": 25,
"start_index": -1
},
"_meta": {
"title": "Get Image or Mask Range From Batch"
}
},
"994:969:859": {
"class_type": "LTXVAudioVideoMask",
"inputs": {
"audio_end_time": [
"994:857",
0
],
"audio_latent": [
"994:969:824",
0
],
"audio_start_time": [
"994:857",
0
],
"existing_mask_mode": "add",
"max_length": "pad",
"video_end_time": [
"994:857",
0
],
"video_fps": [
"994:1001",
0
],
"video_latent": [
"994:969:900",
0
],
"video_start_time": 1
},
"_meta": {
"title": "LTXVAudioVideoMask"
}
},
"994:969:862": {
"class_type": "TrimAudioDuration",
"inputs": {
"audio": [
"994:890",
3
],
"duration": [
"994:857",
0
],
"start_index": 9
},
"_meta": {
"title": "Trim Audio Duration"
}
},
"994:969:896": {
"class_type": "LTXVAddGuideMulti",
"inputs": {
"latent": [
"994:969:859",
0
],
"negative": [
"994:927",
1
],
"num_guides": "2",
"num_guides.frame_idx_1": 0,
"num_guides.frame_idx_2": -1,
"num_guides.image_1": [
"994:923",
0
],
"num_guides.image_2": [
"994:923",
0
],
"num_guides.strength_1": 1,
"num_guides.strength_2": 0.5,
"positive": [
"994:927",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "LTXVAddGuideMulti"
}
},
"994:969:900": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"994:969:843",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"994:969:901": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"994:969:832",
2
],
"temporal_overlap": 16,
"temporal_size": 256,
"tile_size": 1024,
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"994:969:953": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "lcm"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"994:969:954": {
"class_type": "LTXVScheduler",
"inputs": {
"base_shift": 0.95,
"latent": [
"994:842",
0
],
"max_shift": 2.05,
"steps": 8,
"stretch": True,
"terminal": 0.1
},
"_meta": {
"title": "LTXVScheduler"
}
},
"994:969:987": {
"class_type": "ImageBatchExtendWithOverlap",
"inputs": {
"new_images": [
"994:969:901",
0
],
"overlap": 25,
"overlap_mode": "filmic_crossfade",
"overlap_side": "source",
"source_images": [
"994:978:826",
0
]
},
"_meta": {
"title": "Image Batch Extend With Overlap"
}
},
"994:978:817": {
"class_type": "SetLatentNoiseMask",
"inputs": {
"mask": [
"994:978:818",
0
],
"samples": [
"994:978:907",
0
]
},
"_meta": {
"title": "Set Latent Noise Mask"
}
},
"994:978:818": {
"class_type": "SolidMask",
"inputs": {
"height": 512,
"value": 0,
"width": 512
},
"_meta": {
"title": "Create Solid Mask"
}
},
"994:978:822": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"994:978:817",
0
],
"video_latent": [
"994:842",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"994:978:825": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"994:978:883",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"994:978:826": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"994:978:825",
0
],
"temporal_overlap": 16,
"temporal_size": 128,
"tile_size": 1024,
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"994:978:828": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"994:933",
0
],
"negative": [
"994:927",
1
],
"positive": [
"994:927",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"994:978:863": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 44
},
"_meta": {
"title": "RandomNoise"
}
},
"994:978:883": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"994:978:828",
0
],
"latent_image": [
"994:978:822",
0
],
"noise": [
"994:978:863",
0
],
"sampler": [
"994:978:944",
0
],
"sigmas": [
"994:978:939",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"994:978:907": {
"class_type": "LTXVAudioVAEEncode",
"inputs": {
"audio": [
"994:978:991",
0
],
"audio_vae": [
"994:895",
0
]
},
"_meta": {
"title": "LTXV Audio VAE Encode"
}
},
"994:978:939": {
"class_type": "LTXVScheduler",
"inputs": {
"base_shift": 0.95,
"latent": [
"994:842",
0
],
"max_shift": 2.05,
"steps": 8,
"stretch": True,
"terminal": 0.1
},
"_meta": {
"title": "LTXVScheduler"
}
},
"994:978:944": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "lcm"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"994:978:991": {
"class_type": "TrimAudioDuration",
"inputs": {
"audio": [
"994:890",
3
],
"duration": [
"994:857",
0
],
"start_index": 0
},
"_meta": {
"title": "Trim Audio Duration"
}
},
"994:983": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"994:892",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"994:1001",
0
],
"images": [
"994:978:826",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"994:988:823": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"994:988:824": {
"class_type": "LTXVAudioVAEEncode",
"inputs": {
"audio": [
"994:988:862",
0
],
"audio_vae": [
"994:895",
0
]
},
"_meta": {
"title": "LTXV Audio VAE Encode"
}
},
"994:988:827": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"994:988:830",
0
],
"latent_image": [
"994:988:829",
0
],
"noise": [
"994:988:823",
0
],
"sampler": [
"994:988:953",
0
],
"sigmas": [
"994:988:954",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"994:988:829": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"994:988:859",
1
],
"video_latent": [
"994:988:896",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"994:988:830": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"994:933",
0
],
"negative": [
"994:988:896",
1
],
"positive": [
"994:988:896",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"994:988:831": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"994:988:827",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"994:988:832": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"994:988:831",
0
],
"negative": [
"994:988:896",
1
],
"positive": [
"994:988:896",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"994:988:843": {
"class_type": "GetImageRangeFromBatch",
"inputs": {
"images": [
"994:969:987",
2
],
"num_frames": 25,
"start_index": -1
},
"_meta": {
"title": "Get Image or Mask Range From Batch"
}
},
"994:988:859": {
"class_type": "LTXVAudioVideoMask",
"inputs": {
"audio_end_time": [
"994:857",
0
],
"audio_latent": [
"994:988:824",
0
],
"audio_start_time": [
"994:857",
0
],
"existing_mask_mode": "add",
"max_length": "pad",
"video_end_time": [
"994:857",
0
],
"video_fps": [
"994:1001",
0
],
"video_latent": [
"994:988:900",
0
],
"video_start_time": 1
},
"_meta": {
"title": "LTXVAudioVideoMask"
}
},
"994:988:862": {
"class_type": "TrimAudioDuration",
"inputs": {
"audio": [
"994:890",
3
],
"duration": [
"994:857",
0
],
"start_index": 18
},
"_meta": {
"title": "Trim Audio Duration"
}
},
"994:988:896": {
"class_type": "LTXVAddGuideMulti",
"inputs": {
"latent": [
"994:988:859",
0
],
"negative": [
"994:927",
1
],
"num_guides": "2",
"num_guides.frame_idx_1": 0,
"num_guides.frame_idx_2": -1,
"num_guides.image_1": [
"994:923",
0
],
"num_guides.image_2": [
"994:923",
0
],
"num_guides.strength_1": 1,
"num_guides.strength_2": 0.5,
"positive": [
"994:927",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "LTXVAddGuideMulti"
}
},
"994:988:900": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"994:988:843",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"994:988:901": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"994:988:832",
2
],
"temporal_overlap": 16,
"temporal_size": 256,
"tile_size": 1024,
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"994:988:953": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "lcm"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"994:988:954": {
"class_type": "LTXVScheduler",
"inputs": {
"base_shift": 0.95,
"latent": [
"994:842",
0
],
"max_shift": 2.05,
"steps": 8,
"stretch": True,
"terminal": 0.1
},
"_meta": {
"title": "LTXVScheduler"
}
},
"994:988:987": {
"class_type": "ImageBatchExtendWithOverlap",
"inputs": {
"new_images": [
"994:988:901",
0
],
"overlap": 25,
"overlap_mode": "filmic_crossfade",
"overlap_side": "source",
"source_images": [
"994:969:987",
2
]
},
"_meta": {
"title": "Image Batch Extend With Overlap"
}
},
"994:989:823": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"994:989:824": {
"class_type": "LTXVAudioVAEEncode",
"inputs": {
"audio": [
"994:989:862",
0
],
"audio_vae": [
"994:895",
0
]
},
"_meta": {
"title": "LTXV Audio VAE Encode"
}
},
"994:989:827": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"994:989:830",
0
],
"latent_image": [
"994:989:829",
0
],
"noise": [
"994:989:823",
0
],
"sampler": [
"994:989:953",
0
],
"sigmas": [
"994:989:954",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"994:989:829": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"994:989:859",
1
],
"video_latent": [
"994:989:896",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"994:989:830": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"994:933",
0
],
"negative": [
"994:989:896",
1
],
"positive": [
"994:989:896",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"994:989:831": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"994:989:827",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"994:989:832": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"994:989:831",
0
],
"negative": [
"994:989:896",
1
],
"positive": [
"994:989:896",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"994:989:843": {
"class_type": "GetImageRangeFromBatch",
"inputs": {
"images": [
"994:988:987",
2
],
"num_frames": 25,
"start_index": -1
},
"_meta": {
"title": "Get Image or Mask Range From Batch"
}
},
"994:989:859": {
"class_type": "LTXVAudioVideoMask",
"inputs": {
"audio_end_time": [
"994:857",
0
],
"audio_latent": [
"994:989:824",
0
],
"audio_start_time": [
"994:857",
0
],
"existing_mask_mode": "add",
"max_length": "pad",
"video_end_time": [
"994:857",
0
],
"video_fps": [
"994:1001",
0
],
"video_latent": [
"994:989:900",
0
],
"video_start_time": 1
},
"_meta": {
"title": "LTXVAudioVideoMask"
}
},
"994:989:862": {
"class_type": "TrimAudioDuration",
"inputs": {
"audio": [
"994:890",
3
],
"duration": [
"994:857",
0
],
"start_index": 27
},
"_meta": {
"title": "Trim Audio Duration"
}
},
"994:989:896": {
"class_type": "LTXVAddGuideMulti",
"inputs": {
"latent": [
"994:989:859",
0
],
"negative": [
"994:927",
1
],
"num_guides": "2",
"num_guides.frame_idx_1": 0,
"num_guides.frame_idx_2": -1,
"num_guides.image_1": [
"994:923",
0
],
"num_guides.image_2": [
"994:923",
0
],
"num_guides.strength_1": 1,
"num_guides.strength_2": 0.5,
"positive": [
"994:927",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "LTXVAddGuideMulti"
}
},
"994:989:900": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"994:989:843",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"994:989:901": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"994:989:832",
2
],
"temporal_overlap": 16,
"temporal_size": 256,
"tile_size": 1024,
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"994:989:953": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "lcm"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"994:989:954": {
"class_type": "LTXVScheduler",
"inputs": {
"base_shift": 0.95,
"latent": [
"994:842",
0
],
"max_shift": 2.05,
"steps": 8,
"stretch": True,
"terminal": 0.1
},
"_meta": {
"title": "LTXVScheduler"
}
},
"994:989:987": {
"class_type": "ImageBatchExtendWithOverlap",
"inputs": {
"new_images": [
"994:989:901",
0
],
"overlap": 25,
"overlap_mode": "filmic_crossfade",
"overlap_side": "source",
"source_images": [
"994:988:987",
2
]
},
"_meta": {
"title": "Image Batch Extend With Overlap"
}
},
"994:990:823": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"994:990:824": {
"class_type": "LTXVAudioVAEEncode",
"inputs": {
"audio": [
"994:990:862",
0
],
"audio_vae": [
"994:895",
0
]
},
"_meta": {
"title": "LTXV Audio VAE Encode"
}
},
"994:990:827": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"994:990:830",
0
],
"latent_image": [
"994:990:829",
0
],
"noise": [
"994:990:823",
0
],
"sampler": [
"994:990:953",
0
],
"sigmas": [
"994:990:954",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"994:990:829": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"994:990:859",
1
],
"video_latent": [
"994:990:896",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"994:990:830": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"994:933",
0
],
"negative": [
"994:990:896",
1
],
"positive": [
"994:990:896",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"994:990:831": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"994:990:827",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"994:990:832": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"994:990:831",
0
],
"negative": [
"994:990:896",
1
],
"positive": [
"994:990:896",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"994:990:843": {
"class_type": "GetImageRangeFromBatch",
"inputs": {
"images": [
"994:989:987",
2
],
"num_frames": 25,
"start_index": -1
},
"_meta": {
"title": "Get Image or Mask Range From Batch"
}
},
"994:990:859": {
"class_type": "LTXVAudioVideoMask",
"inputs": {
"audio_end_time": [
"994:857",
0
],
"audio_latent": [
"994:990:824",
0
],
"audio_start_time": [
"994:857",
0
],
"existing_mask_mode": "add",
"max_length": "pad",
"video_end_time": [
"994:857",
0
],
"video_fps": [
"994:1001",
0
],
"video_latent": [
"994:990:900",
0
],
"video_start_time": 1
},
"_meta": {
"title": "LTXVAudioVideoMask"
}
},
"994:990:862": {
"class_type": "TrimAudioDuration",
"inputs": {
"audio": [
"994:890",
3
],
"duration": [
"994:857",
0
],
"start_index": 36
},
"_meta": {
"title": "Trim Audio Duration"
}
},
"994:990:896": {
"class_type": "LTXVAddGuideMulti",
"inputs": {
"latent": [
"994:990:859",
0
],
"negative": [
"994:927",
1
],
"num_guides": "2",
"num_guides.frame_idx_1": 0,
"num_guides.frame_idx_2": -1,
"num_guides.image_1": [
"994:923",
0
],
"num_guides.image_2": [
"994:923",
0
],
"num_guides.strength_1": 1,
"num_guides.strength_2": 0.5,
"positive": [
"994:927",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "LTXVAddGuideMulti"
}
},
"994:990:900": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"994:990:843",
0
],
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"994:990:901": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"994:990:832",
2
],
"temporal_overlap": 16,
"temporal_size": 256,
"tile_size": 1024,
"vae": [
"994:904",
0
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"994:990:953": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "lcm"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"994:990:954": {
"class_type": "LTXVScheduler",
"inputs": {
"base_shift": 0.95,
"latent": [
"994:842",
0
],
"max_shift": 2.05,
"steps": 8,
"stretch": True,
"terminal": 0.1
},
"_meta": {
"title": "LTXVScheduler"
}
},
"994:990:987": {
"class_type": "ImageBatchExtendWithOverlap",
"inputs": {
"new_images": [
"994:990:901",
0
],
"overlap": 25,
"overlap_mode": "filmic_crossfade",
"overlap_side": "source",
"source_images": [
"994:989:987",
2
]
},
"_meta": {
"title": "Image Batch Extend With Overlap"
}
},
"994:995": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"994:892",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"994:1001",
0
],
"images": [
"994:990:987",
2
]
},
"_meta": {
"title": "Create Video"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)Preguntas y respuestas
Si tu salida es negra, detén la ejecución de inmediato y reduce la resolución de tus entradas. Esto puede ayudar a resolver el problema.
El flujo soporta formatos de audio comunes como MP3 y WAV. Asegúrate de que tu archivo esté en un formato compatible antes de subirlo.
El modelo LTX-2 es experimental y se recomienda para proyectos creativos donde la variabilidad es aceptable. No se recomienda para aplicaciones precisas o comerciales.
Asegúrate de que tu archivo de audio sea claro y bien definido. Ajusta la configuración en los 'comfyui-kjnodes' para afinar la sincronización.
Flujos de trabajo relacionados
- LTX-2
Comprime cualquier cosa con LTX-2 I2V y LoRA
- LTX-2, Lightricks
LTX-2 De Profundidad a Video
- LTX-2, Lightricks
LTX-2 Detección de Bordes a Video
- LTX-2, Lightricks
LTX-2 Imagen a vídeo (Destilado)
- LTX-2, Lightricks
LTX-2 Pose a Video
- LTX-2, Lightricks
LTX-2 Texto a Vídeo
- LTX-2, Lightricks
LTX-2 Texto a vídeo (Destilado)
- LTX-2, Lightricks
LTX-2: Imagen a Vídeo
- LTX-2, Lightricks
LTX-2: Texto a Vídeo