LTX-2.3 : Image et audio en vidéo
Téléchargez une image et un fichier audio pour générer une vidéo de haute qualité avec des mouvements de lèvres synchronisés en utilisant LTX-2.3.
Dans le workflow
Un aperçu en lecture seule du modèle source. Ouvrez-le dans Cloud pour explorer les nœuds et apporter des modifications.
Loading the graph
Open full-size workflow previewAppelez ce modèle depuis votre code
La requête ci-dessous utilise le même graphe préparé et les mêmes paramètres que le Playground. Chaque envoi peut lancer une exécution payante ; ne relancez pas automatiquement un envoi dont l’issue est inconnue.
What you need
- Runs on
- Comfy Cloud
- Clé
- COMFY_API_KEY
- Vos fichiers
- Importés par le code depuis leurs URL
Nécessite un forfait Cloud payant et des crédits.
# 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({
"269": {
"class_type": "LoadImage",
"inputs": {
"image": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Load Image"
}
},
"276": {
"class_type": "LoadAudio",
"inputs": {
"audio": "UPLOADED_audio_FILENAME"
},
"_meta": {
"title": "Load Audio"
}
},
"341": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/LTX_2.3_ia2v",
"format": "auto",
"format.codec": "auto",
"video": [
"340:312",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"340:285": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"340:286": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 923652788975261
},
"_meta": {
"title": "RandomNoise"
}
},
"340:287": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"340:309",
1
],
"video_latent": [
"340:296",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"340:288": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_cfg_pp"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"340:289": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "0.85, 0.7250, 0.4219, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"340:290": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"340:293",
0
],
"negative": [
"340:292",
1
],
"positive": [
"340:292",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"340:291": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"340:315",
0
],
"latent_image": [
"340:326",
0
],
"noise": [
"340:286",
0
],
"sampler": [
"340:298",
0
],
"sigmas": [
"340:308",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"340:292": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"340:309",
0
],
"negative": [
"340:307",
1
],
"positive": [
"340:307",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"340:293": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2.3-22b-distilled-lora-384.safetensors",
"model": [
"340:317",
0
],
"strength_model": 0.5
},
"_meta": {
"title": "Load LoRA"
}
},
"340:294": {
"class_type": "ResizeImagesByLongerEdge",
"inputs": {
"images": [
"340:297",
0
],
"longer_edge": 1536
},
"_meta": {
"title": "Resize Images by Longer Edge (DEPRECATED)"
}
},
"340:295": {
"class_type": "LTXVLatentUpsampler",
"inputs": {
"samples": [
"340:309",
0
],
"upscale_model": [
"340:313",
0
],
"vae": [
"340:317",
2
]
},
"_meta": {
"title": "LTXVLatentUpsampler"
}
},
"340:296": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"340:305",
0
],
"image": [
"340:334",
0
],
"latent": [
"340:295",
0
],
"strength": 1,
"vae": [
"340:317",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"340:297": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"269",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": [
"340:324",
0
],
"resize_type.width": [
"340:330",
0
],
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"340:298": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_ancestral_cfg_pp"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"340:299": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"340:330",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"340:301": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"340:324",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"340:302": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"340:301",
1
],
"length": [
"340:329",
1
],
"width": [
"340:299",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"340:303": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"340:335",
0
],
"samples": [
"340:311",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"340:304": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a",
"values.a": [
"340:323",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"340:305": {
"class_type": "PrimitiveBoolean",
"inputs": {
"value": False
},
"_meta": {
"title": "Switch to Text to Video?"
}
},
"340:306": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"340:318",
0
],
"text": [
"340:342",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"340:307": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"340:304",
0
],
"negative": [
"340:314",
0
],
"positive": [
"340:306",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"340:308": {
"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"
}
},
"340:309": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"340:291",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"340:310": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"340:290",
0
],
"latent_image": [
"340:287",
0
],
"noise": [
"340:285",
0
],
"sampler": [
"340:288",
0
],
"sigmas": [
"340:289",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"340:311": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"340:310",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"340:312": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"340:303",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"340:304",
0
],
"images": [
"340:316",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"340:313": {
"class_type": "LatentUpscaleModelLoader",
"inputs": {
"model_name": "ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
},
"_meta": {
"title": "Load Latent Upscale Model"
}
},
"340:314": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"340:318",
0
],
"text": "pc game, console game, video game, cartoon, childish, ugly"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"340:315": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"340:293",
0
],
"negative": [
"340:307",
1
],
"positive": [
"340:307",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"340:316": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"340:311",
0
],
"temporal_overlap": 4,
"temporal_size": 4096,
"tile_size": 768,
"vae": [
"340:317",
2
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"340:317": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"340:318": {
"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"
}
},
"340:319": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "A black and white film-noir scene in one continuous medium close-up with no cuts. The woman sits still in a dark, bare room, looking straight into the camera as she speaks in a low, measured voice, her lips moving clearly with every word. Slatted light from unseen window blinds lies across her face, shoulders and the wall behind her, and the bars of light slowly crawl upward as if a car is passing outside. She pauses, glances briefly to her side, then looks back into the lens and lowers her voice for the last words. The camera holds steady at chest height with only a very slow, subtle push-in toward her face. Heavy film grain, a soft light flicker, quiet room tone, no music."
},
"_meta": {
"title": "Prompt"
}
},
"340:323": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 24
},
"_meta": {
"title": "Frame Rate"
}
},
"340:324": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Height"
}
},
"340:325": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"340:305",
0
],
"image": [
"340:334",
0
],
"latent": [
"340:302",
0
],
"strength": 0.7,
"vae": [
"340:317",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"340:326": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"340:327",
0
],
"video_latent": [
"340:325",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"340:327": {
"class_type": "SetLatentNoiseMask",
"inputs": {
"mask": [
"340:333",
0
],
"samples": [
"340:328",
0
]
},
"_meta": {
"title": "Set Latent Noise Mask"
}
},
"340:328": {
"class_type": "LTXVAudioVAEEncode",
"inputs": {
"audio": [
"340:332",
0
],
"audio_vae": [
"340:335",
0
]
},
"_meta": {
"title": "LTXV Audio VAE Encode"
}
},
"340:329": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a * b + 1",
"values.a": [
"340:331",
0
],
"values.b": [
"340:323",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"340:330": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1280
},
"_meta": {
"title": "Width"
}
},
"340:331": {
"class_type": "PrimitiveFloat",
"inputs": {
"value": 10
},
"_meta": {
"title": "Duration"
}
},
"340:332": {
"class_type": "TrimAudioDuration",
"inputs": {
"audio": [
"276",
0
],
"duration": [
"340:331",
0
],
"start_index": 0
},
"_meta": {
"title": "Trim Audio Duration"
}
},
"340:333": {
"class_type": "SolidMask",
"inputs": {
"height": [
"340:324",
0
],
"value": 0,
"width": [
"340:330",
0
]
},
"_meta": {
"title": "Create Solid Mask"
}
},
"340:334": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"340:294",
0
],
"img_compression": 18
},
"_meta": {
"title": "LTXV Preprocess"
}
},
"340:335": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"340:342": {
"class_type": "TextGenerateLTX2Prompt",
"inputs": {
"clip": [
"340:344",
1
],
"image": [
"340:297",
0
],
"max_length": 256,
"mtp": "auto",
"prompt": [
"340:319",
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"
}
},
"340:343": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"340:342",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"340:344": {
"class_type": "LoraLoader",
"inputs": {
"clip": [
"340:318",
0
],
"lora_name": "gemma-3-12b-it-abliterated_lora_rank64_bf16.safetensors",
"model": [
"340:317",
0
],
"strength_clip": 1,
"strength_model": 1
},
"_meta": {
"title": "Load LoRA (Model and CLIP)"
}
}
})
workflow.set_input("276", "audio", client.assets.from_url("https://comfy.org/catalog-media/b4b5b899-f01d-4073-aa7d-1b917d4e824c/e34f2188-1f07-41c4-b703-6d0c8498f5c9"))
workflow.set_input("269", "image", client.assets.from_url("https://comfy.org/catalog-media/1995606e-723b-4e08-973a-c04e4233a91b/1202f39f-be96-4b13-98cd-c054f6456f36"))
# 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("341"):
output.to_file(output.name)Essayer un exemple
À propos de ce workflow
Ce workflow ComfyUI transforme une image et un enregistrement vocal en une vidéo parlante synchronisée grâce au modèle LTX-2.3. Chargez un portrait via LoadImage et fournissez l’audio via LoadAudio ou enregistrez-le avec RecordAudio. Les deux flux alimentent le générateur LTX-2.3 (98ee9e5b-467b-40aa-a534-36033f27d0b4), qui synthétise une séquence d’images où le sujet parle en synchronisation avec l’audio. Les images générées sont encodées en MP4 via SaveVideo.
Techniquement, LTX-2.3 s’appuie sur l’identité visuelle de l’image de référence et les caractéristiques temporelles de l’audio pour animer la bouche et les mouvements subtils du visage. Le nœud propose généralement des réglages comme la résolution de sortie, le FPS, un seed pour la reproductibilité et un prompt optionnel pour guider le mouvement ou le style. Le MarkdownNote du graphe documente des astuces rapides et des liens vers les dépôts officiels Lightricks pour télécharger les poids nécessaires.
Questions-réponses
Utilisez un portrait de face avec une bonne lumière et la bouche dégagée (pas de mains, micros ou objets couvrant les lèvres). Centrez le visage et utilisez une résolution raisonnable (ex. : 512–1024 px sur le petit côté). Évitez les angles extrêmes et les arrière-plans chargés.
Un audio propre, centré sur la parole, produit les mouvements de bouche les plus précis. Le WAV ou un MP3 à haut débit fonctionnent généralement ; les pistes voix en mono sont à privilégier. Réduisez la réverbération et le bruit de fond pour améliorer l’alignement et le réalisme.
Cela dépend de la version de votre nœud SaveVideo. Certaines variantes peuvent multiplexer l’audio ; d’autres exportent un MP4 muet. Si la vôtre est muette, combinez la vidéo de sortie avec le même audio dans un éditeur ou via une étape de mux séparée.
Commencez avec un portrait clair et centré, et un audio propre. Adaptez les FPS à votre plateforme cible (ex. : 24–30). Si un champ d’invite est disponible, décrivez des mouvements subtils (clignements, petits mouvements de tête) pour éviter un rendu trop statique. Essayez différents seeds pour varier, et envisagez de recadrer plus serré sur le visage si la zone de la bouche paraît trop petite.
Workflows associés
- LTX-2.3
Turn an image into a video
- LTX-2.3
Add camera motion first last frame
- LTX-2.3
Remove an object from a video
- LTX-2.3
Expand a video’s frame
- LTX-2.3
Make your character talk
- LTX-2.3
Animate a scene from a reference sheet
- LTX-2.3
Restore archival footage
- LTX-2.3
Googly Eyes
- ElevenLabs, LTX-2.3
Générer une vidéo UGC avec clone vocal
- LTX-2.3
LTX 2.3 - Anime2Real
- LTX-2.3
LTX 2.3 - EditAnything - Édition vidéo par invite
- LTX-2.3
LTX 2.3 - Feutrine Douillette