Python
{
"$schema": "../../schema/app.schema.json",
"id": "speak",
"name": "Speak",
"section": "video",
"pack": "video-ltx25",
"status": "ready",
"higgsfield_feature": "Speak",
"summary": "A photo says your line out loud: LTX-2.5 makes the voice, the lip sync and the motion in one pass, no TTS model needed.",
"workflow": "workflow.api.json",
"source": {
"template": "video_ltx2_5_i2v.json",
"comfyui": "0.42.0",
"notes": "Unchanged official image-to-video template; the prompt quotes the line, which LTX-2.5 voices with synchronized audio. Voice quality still to check in the lab."
},
"inputs": [
{
"id": "image",
"type": "image",
"label": "Portrait",
"required": true,
"limits": {
"max_mb": 20
},
"bind": [
{
"node": "395",
"field": "image"
}
]
},
{
"id": "line",
"type": "textarea",
"label": "What they say",
"required": true,
"default": "Hi! I am talking to you from a single photo. My voice and my lips come from an open model.",
"help": "One or two sentences fit in five seconds"
},
{
"id": "voice",
"type": "select",
"label": "Voice",
"default": "a warm, friendly female voice",
"options": [
{
"value": "a warm, friendly female voice",
"label": "Warm, female"
},
{
"value": "a calm, deep male voice",
"label": "Calm, male"
},
{
"value": "an excited, energetic voice",
"label": "Excited"
},
{
"value": "a soft, close whisper",
"label": "Whisper"
},
{
"value": "the clear, confident voice of a news anchor",
"label": "News anchor"
},
{
"value": "a relaxed voice with a slight smile",
"label": "Relaxed"
}
]
},
{
"id": "scene",
"type": "textarea",
"label": "Shot (optional)",
"default": "Medium close-up, natural head movement and blinking, soft window light",
"bind": [
{
"node": "398:376",
"field": "value",
"template": "{scene}. The person looks into the camera and speaks in {voice}, with natural lip movement, saying: \"{line}\""
}
]
},
{
"id": "duration",
"type": "slider",
"label": "Seconds",
"min": 3,
"max": 10,
"step": 1,
"default": 5,
"bind": [
{
"node": "398:362",
"field": "value"
}
]
},
{
"id": "enhance",
"type": "toggle",
"label": "Enhance prompt",
"default": false,
"help": "Off by default: the enhancer may rephrase your line",
"bind": [
{
"node": "398:383",
"field": "value"
}
]
},
{
"id": "aspect",
"type": "select",
"label": "Aspect ratio",
"default": "9:16 (Portrait Widescreen)",
"options": [
{
"value": "16:9 (Widescreen)",
"label": "16:9"
},
{
"value": "9:16 (Portrait Widescreen)",
"label": "9:16"
},
{
"value": "1:1 (Square)",
"label": "1:1"
},
{
"value": "4:3 (Standard)",
"label": "4:3"
},
{
"value": "3:4 (Portrait Standard)",
"label": "3:4"
},
{
"value": "21:9 (Ultrawide)",
"label": "21:9"
}
],
"bind": [
{
"node": "403",
"field": "aspect_ratio"
}
]
},
{
"id": "seed",
"type": "seed",
"label": "Seed",
"default": -1,
"help": "-1 picks a random seed",
"bind": [
{
"node": "398:339",
"field": "noise_seed"
}
]
}
],
"outputs": [
{
"node": "75",
"type": "video",
"label": "Video"
}
],
"models": [
{
"repo": "Lightricks/LTX-2.5",
"file": "diffusion_models/ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors",
"dir": "diffusion_models",
"gb": 21.5,
"phase": "denoise",
"gated": true,
"license": "LTX-2.x Community License"
},
{
"repo": "Lightricks/LTX-2.5",
"file": "text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors",
"dir": "text_encoders",
"gb": 15.37,
"phase": "encode",
"gated": true,
"license": "LTX-2.x Community License"
},
{
"repo": "Lightricks/LTX-2.5",
"file": "vae/ltx-2.5-video-vae-bf16.safetensors",
"dir": "vae",
"gb": 1.47,
"phase": "decode",
"gated": true,
"license": "LTX-2.x Community License"
},
{
"repo": "Lightricks/LTX-2.5",
"file": "vae/ltx-2.5-audio-vae-bf16.safetensors",
"dir": "vae",
"gb": 0.36,
"phase": "decode",
"gated": true,
"license": "LTX-2.x Community License"
},
{
"repo": "Lightricks/LTX-2.5",
"file": "latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors",
"dir": "latent_upscale_models",
"gb": 1.0,
"phase": "aux",
"gated": true,
"license": "LTX-2.x Community License"
},
{
"repo": "Comfy-Org/gemma-4",
"file": "text_encoders/gemma4_e2b_it_int8_convrot.safetensors",
"dir": "text_encoders",
"gb": 5.2,
"phase": "encode",
"license": "Apache-2.0",
"optional": true
}
],
"notes": "Use footage and photos of yourself, fictional characters, or people who agreed to it.",
"credits": [
"LTX-2.5 by Lightricks",
"Workflow adapted from ComfyUI's official LTX-2.5 template"
],
"test": {
"image": "test/portrait.png",
"duration": 3
}
}