LTX-2.5:圖像轉影片
使用 LTX-2.5 由單張影像生成高保真影片,具備業界領先的像素品質與原生多鏡頭能力,可於連續場景間保持角色、環境與光線一致。適合電影製作、視覺特效鏡頭製作與需快速本地部署的內容產線。
工作流程內部
來源範本的唯讀預覽。請在 Cloud 中開啟,以探索節點並進行變更。
Loading the graph
Open full-size workflow preview從您的程式碼呼叫此模型
以下請求使用與 Playground 相同的已準備節點圖和設定。每次提交都可能啟動付費執行;若提交結果不明,請勿自動重試提交。
What you need
- Runs on
- Comfy Cloud
- 金鑰
- COMFY_API_KEY
- 您的檔案
- 由程式碼透過其 URL 上傳
需要付費 Cloud 方案與點數。
# 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-2.5_i2v",
"format": "auto",
"format.codec": "auto",
"video": [
"398:370",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"395": {
"class_type": "LoadImage",
"inputs": {
"image": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Load First Frame"
}
},
"403": {
"class_type": "ResolutionSelector",
"inputs": {
"aspect_ratio": "16:9 (Widescreen)",
"megapixels": 0.9,
"multiple": 32
},
"_meta": {
"title": "Resolution Selector"
}
},
"398:338": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"398:339": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 72790129095462
},
"_meta": {
"title": "RandomNoise"
}
},
"398:340": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"398:367",
1
],
"video_latent": [
"398:349",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"398:341": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_ancestral"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"398:344": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"398:388",
0
],
"latent_image": [
"398:377",
0
],
"noise": [
"398:339",
0
],
"sampler": [
"398:352",
0
],
"sigmas": [
"398:397",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"398:348": {
"class_type": "LTXVLatentUpsampler",
"inputs": {
"samples": [
"398:367",
0
],
"upscale_model": [
"398:371",
0
],
"vae": [
"398:385",
0
]
},
"_meta": {
"title": "LTXVLatentUpsampler"
}
},
"398:349": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"398:363",
0
],
"image": [
"398:350",
0
],
"latent": [
"398:348",
0
],
"strength": 1,
"vae": [
"398:385",
0
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"398:350": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"398:351",
0
],
"img_compression": 18
},
"_meta": {
"title": "LTXV Preprocess"
}
},
"398:351": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"395",
0
],
"resize_type": "scale longer dimension",
"resize_type.longer_size": 1536,
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"398:352": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_ancestral"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"398:353": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"398:372",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"398:355": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"398:360",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"398:356": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"398:355",
1
],
"length": [
"398:378",
1
],
"width": [
"398:353",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"398:357": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"398:363",
0
],
"image": [
"398:350",
0
],
"latent": [
"398:356",
0
],
"strength": 0.7,
"vae": [
"398:385",
0
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"398:358": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"398:386",
0
],
"samples": [
"398:369",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"398:359": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a",
"values.a": [
"398:361",
0
]
},
"_meta": {
"title": "Math Expression (fps)"
}
},
"398:360": {
"class_type": "PrimitiveInt",
"inputs": {
"value": [
"403",
1
]
},
"_meta": {
"title": "Height"
}
},
"398:361": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 24
},
"_meta": {
"title": "Frame Rate"
}
},
"398:362": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 5
},
"_meta": {
"title": "Duration"
}
},
"398:363": {
"class_type": "PrimitiveBoolean",
"inputs": {
"value": False
},
"_meta": {
"title": "Switch to Text to Video?"
}
},
"398:364": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"398:387",
0
],
"text": [
"398:382",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"398:365": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"398:359",
0
],
"negative": [
"398:373",
0
],
"positive": [
"398:364",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"398:366": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"398:386",
0
],
"batch_size": 1,
"frame_rate": [
"398:359",
1
],
"frames_number": [
"398:378",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"398:367": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"398:344",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"398:368": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"398:391",
0
],
"latent_image": [
"398:340",
0
],
"noise": [
"398:338",
0
],
"sampler": [
"398:341",
0
],
"sigmas": [
"398:396",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"398:369": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"398:368",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"398:370": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"398:358",
0
],
"bit_depth": 8,
"codec": "none",
"color_space": "sRGB",
"fps": [
"398:359",
0
],
"images": [
"398:374",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"398:371": {
"class_type": "LatentUpscaleModelLoader",
"inputs": {
"model_name": "ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors"
},
"_meta": {
"title": "Load Latent Upscale Model"
}
},
"398:372": {
"class_type": "PrimitiveInt",
"inputs": {
"value": [
"403",
0
]
},
"_meta": {
"title": "Width"
}
},
"398:373": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"398:387",
0
],
"text": "pc game, console game, video game, cartoon, childish, ugly"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"398:374": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"398:369",
0
],
"temporal_overlap": 32,
"temporal_size": 4096,
"tile_size": 768,
"vae": [
"398:385",
0
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"398:376": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "Use the provided start image as the first frame. The large moth resting on the bridge of the person's nose slowly opens and closes its patterned wings, the eyespots catching the golden light, its fuzzy antennae twitching. The person breathes calmly, then blinks once and turns their head a few degrees toward the camera, a faint glow pulsing in the amber lens flare that streaks from the corner of the eye across the darkness. Tiny golden dust motes drift through the beam. The camera starts in a medium close-up and makes a slow, smooth push-in toward the face, settling on the moth's wings and the person's steady gaze. Hard side light rakes across the gold-tinted skin, showing fine texture. Soft ambient hum, the faint flutter of wings. Surreal, cinematic, intimate."
},
"_meta": {
"title": "Prompt"
}
},
"398:377": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"398:366",
0
],
"video_latent": [
"398:357",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"398:378": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a * b + 1",
"values.a": [
"398:362",
0
],
"values.b": [
"398:361",
0
]
},
"_meta": {
"title": "Math Expression (length)"
}
},
"398:380": {
"class_type": "TextGenerateLTX2Prompt",
"inputs": {
"clip": [
"398:393",
0
],
"image": [
"398:350",
0
],
"max_length": 600,
"mtp": "auto",
"prompt": [
"398:376",
0
],
"sampling_mode": "on",
"sampling_mode.min_p": 0.05,
"sampling_mode.presence_penalty": 0,
"sampling_mode.repetition_penalty": 1.15,
"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"
}
},
"398:381": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"398:382",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"398:382": {
"class_type": "ComfySwitchNode",
"inputs": {
"on_false": [
"398:376",
0
],
"on_true": [
"398:380",
0
],
"switch": [
"398:383",
0
]
},
"_meta": {
"title": "If/Else Switch"
}
},
"398:383": {
"class_type": "PrimitiveBoolean",
"inputs": {
"value": True
},
"_meta": {
"title": "Boolean (Enable Prompt Enhance)"
}
},
"398:384": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"398:385": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "ltx-2.5-video-vae-bf16.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"398:386": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "ltx-2.5-audio-vae-bf16.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"398:387": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors",
"device": "default",
"type": "ltxv"
},
"_meta": {
"title": "Load CLIP"
}
},
"398:388": {
"class_type": "LTXVDualCFGGuider",
"inputs": {
"audio_cfg": 1,
"model": [
"398:384",
0
],
"negative": [
"398:365",
1
],
"positive": [
"398:365",
0
],
"video_cfg": 1
},
"_meta": {
"title": "LTXV Dual CFG Guider"
}
},
"398:391": {
"class_type": "LTXVDualCFGGuider",
"inputs": {
"audio_cfg": 1,
"model": [
"398:384",
0
],
"negative": [
"398:365",
1
],
"positive": [
"398:365",
0
],
"video_cfg": 1
},
"_meta": {
"title": "LTXV Dual CFG Guider"
}
},
"398:393": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "gemma4_e2b_it_bf16.safetensors",
"device": "default",
"type": "ltxv"
},
"_meta": {
"title": "Load CLIP"
}
},
"398:396": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "0.85, 0.7250, 0.4219, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"398:397": {
"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"
}
}
})
workflow.set_input("395", "image", client.assets.from_url("https://comfy.org/catalog-media/c7c6e297-c2be-4973-b40d-6e5b81b8790c/fc248d53-6694-4fa1-a96f-02529c17a9fe"))
# 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)試試範例
關於此工作流程
這個 ComfyUI 工作流程可將單一靜態影像轉換為流暢高保真影片,採用 Lightricks 的 LTX-2.5 開源影片生成模型。流程設計簡潔且適合製作:LoadImage 載入來源影格,ResolutionSelector 鎖定模型友善尺寸(32 的倍數)與長寬比,LTX-2.5 生成節點(UUID: 6e397a2b-68f7-48f6-8930-f3a5491a163c)合成連貫動作序列,SaveVideo 將影格編碼為可用 MP4。流程中有 MarkdownNote 提供 UI 內指引與連結。
技術上,LTX-2.5 採用關鍵影格優先「Pixel Diffusion」方法,能在時間軸上穩定傳遞細節與結構,有助於從來源圖保留主體、光線與場景構圖,同時引入可控動作。ResolutionSelector 確保你選定的 16:9 尺寸符合模型步幅(32 的倍數),這對穩定性與 VRAM 效率至關重要。流程全程本地運行,可快速迭代、調整長度(影格數/FPS)與動作強度,滿足預視、特效開發與內容產線需求。
問答
LTX-2.5(和許多擴散模型一樣)會在對齊步幅的尺寸上運作。使用 32 的倍數可避免內部補邊/縮放造成的瑕疵、提升穩定性,並更省 VRAM。ResolutionSelector 節點可協助你選取有效的 16:9 尺寸(例如 1056x608,約 0.6 MP)。
片段時長 = 影格數 ÷ FPS(例如 96 影格在 24 FPS ≈ 4 秒)。算圖時間與記憶體會隨解析度、影格數以及運動複雜度成長。建議先用較保守的設定(例如 0.6–0.8 MP、64–96 影格、16–24 FPS),再依你的 VRAM 與迭代時間逐步提高。
使用乾淨、高解析度且主體與光線清楚的來源圖片。保持輸出解析度為步幅對齊,降低運動強度以獲得更保守的動作,並可考慮提高 FPS 同時維持中等運動量。若出現不想要的瑕疵就重新設 seed;通常試幾次後穩定度會改善。
此範本聚焦於單一影像轉影片片段。LTX-2.5 的設計目標是在鏡頭之間維持一致的風格與身分;但若要在 ComfyUI 中建立多鏡頭時間軸,可用 Subgraph 複製這個區塊來算每個鏡頭,並在剪輯軟體(或用獨立的合併步驟)將輸出的片段串接起來。
相關工作流程
- LTX-2.3
Turn an image into a video
- MiniMax H3
Create a video from references
- LTX-2.3
Add camera motion first last frame
- Wan2.2
1.2 入門範本-圖像轉影片
- 合作夥伴節點
AI on the Lot 2026 - LTX-2.3 - i2v
- Google Gemini, Kling 3.0, Z-Image-Turbo
AIrt MAchIne(API 版本)
- SSD1.5
AnimateDiff - IPAdapters 迴圈動畫
- Seedance1.0 Pro, ByteDance
ByteDance: 起始結束到影片
- 合合作夥伴節點
FastVideo FastH3: Text to Video
- Flux
FLUX 3 影片:文字轉影片
- Flux
FLUX 3 影片:文字轉影片
- 合作夥伴節點
Gemini Omni 1.1 Flash: Image to Video