LTX-2.3 風格過渡
應用ltx2.3-transition LoRA來建立平滑的風格和場景過渡。此工作流程使用一個專門的模型來融合視覺元素。
關於
此 ComfyUI 工作流程在 LTX-2.3 文字轉影片模型之上,透過套用 ltx2.3-transition LoRA 建立可引導的風格與場景轉場。核心生成在自訂 LTX-2.3 管線節點(beb19732-5803-4af6-b2d2-289692ce780b)中完成:它接收你的提示詞、以你設定的權重套用 LoRA,並渲染一段影格序列,讓畫面從一種風格或場景描述平滑演變到另一種。如果你用 LoadImage 提供參考圖片,管線也能把色盤或主體線索帶入轉場;若不提供,轉場就完全由文字引導。
實用控制集中在需要調整的地方:提示詞欄位(支援觸發詞「zhuanchang」)、幀數與 FPS 用來控時長,以及 LoRA 強度用來調整轉場表現的明顯程度。內嵌的 MarkdownNote 讓你在反覆嘗試時隨時看到提示詞要點,而 SaveVideo 會依你選擇的幀率與品質把最終影格編碼成影片檔。結果是一種可靠、適合做循環的方式,用來混合視覺元素——風格、光線、主體重點,甚至場景構圖——而不需要手動動畫或後製交叉淡化。
您提供的內容
- 正在讀取工作流程
在 ComfyUI 中執行。 此工作流程無法在此頁面上執行。請在已載入所有內容的 Comfy Cloud 中開啟,或下載到您自己的 ComfyUI。
在 Cloud 中試用工作流程內部
節點圖的唯讀預覽。請在 Comfy Cloud 中開啟,或下載後編輯節點。
Loading the graph
Open full-size workflow preview從程式碼使用此工作流程
可行時會根據工作流程圖和輸入內容產生;否則會顯示儲存的範例。執行可能產生費用的程式碼前,請檢查認證資訊和端點。
What you need
- Runs on
- Comfy Cloud
- 金鑰
- COMFY_API_KEY
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({
"68": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ltx2.3_flf2v",
"format": "auto",
"format.codec": "auto",
"video": [
"139:122",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"137": {
"class_type": "LoadImage",
"inputs": {
"image": "ltx23_flf2v_last_frame.png"
},
"_meta": {
"title": "Load Image"
}
},
"138": {
"class_type": "LoadImage",
"inputs": {
"image": "ltx23_flf2v_first_frame.png"
},
"_meta": {
"title": "Load Image"
}
},
"139:100": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 767871932424233
},
"_meta": {
"title": "RandomNoise"
}
},
"139:101": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"139:126",
0
],
"batch_size": 1,
"frame_rate": [
"139:114",
0
],
"frames_number": [
"139:144",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"139:103": {
"class_type": "LTXAVTextEncoderLoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-distilled-fp8.safetensors",
"device": "default",
"text_encoder": "gemma_3_12B_it_fp4_mixed.safetensors"
},
"_meta": {
"title": "Load LTXV Audio Text Encoder"
}
},
"139:104": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"139:124",
0
],
"img_compression": 25
},
"_meta": {
"title": "LTXV Preprocess"
}
},
"139:105": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"139:106",
2
],
"temporal_overlap": 64,
"temporal_size": 4096,
"tile_size": 768,
"vae": [
"139:127",
2
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"139:106": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"139:121",
0
],
"negative": [
"139:111",
1
],
"positive": [
"139:111",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"139:107": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"139:126",
0
],
"samples": [
"139:121",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"139:108": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"139:110",
1
],
"length": [
"139:144",
1
],
"width": [
"139:110",
0
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"139:109": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"139:123",
0
],
"negative": [
"139:112",
0
],
"positive": [
"139:128",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"139:110": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"139:124",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"139:111": {
"class_type": "LTXVAddGuide",
"inputs": {
"frame_idx": -1,
"image": [
"139:99",
0
],
"latent": [
"139:115",
2
],
"negative": [
"139:115",
1
],
"positive": [
"139:115",
0
],
"strength": 0.7,
"vae": [
"139:127",
2
]
},
"_meta": {
"title": "LTXVAddGuide"
}
},
"139:112": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"139:103",
0
],
"text": "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"139:113": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Width"
}
},
"139:114": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 25
},
"_meta": {
"title": "Frame Rate(int)"
}
},
"139:115": {
"class_type": "LTXVAddGuide",
"inputs": {
"frame_idx": 0,
"image": [
"139:104",
0
],
"latent": [
"139:108",
0
],
"negative": [
"139:109",
1
],
"positive": [
"139:109",
0
],
"strength": 0.7,
"vae": [
"139:127",
2
]
},
"_meta": {
"title": "LTXVAddGuide"
}
},
"139:116": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"139:129",
0
],
"negative": [
"139:111",
1
],
"positive": [
"139:111",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"139:117": {
"class_type": "SamplerEulerAncestral",
"inputs": {
"eta": 0,
"s_noise": 1
},
"_meta": {
"title": "SamplerEulerAncestral"
}
},
"139:118": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "1., 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"139:119": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"139:101",
0
],
"video_latent": [
"139:111",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"139:120": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"139:116",
0
],
"latent_image": [
"139:119",
0
],
"noise": [
"139:100",
0
],
"sampler": [
"139:117",
0
],
"sigmas": [
"139:118",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"139:121": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"139:120",
1
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"139:122": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"139:107",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"139:123",
0
],
"images": [
"139:105",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"139:123": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a",
"values.a": [
"139:114",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"139:124": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"138",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": [
"139:98",
0
],
"resize_type.width": [
"139:113",
0
],
"scale_method": "nearest-exact"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"139:125": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"137",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": [
"139:98",
0
],
"resize_type.width": [
"139:113",
0
],
"scale_method": "nearest-exact"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"139:126": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-distilled-fp8.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"139:127": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2.3-22b-distilled-fp8.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"139:128": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"139:103",
0
],
"text": "The red hair wizard girl looks up as the magical flame burns in her palm. Camera dollys out. The scene turns from a professional photography to a wet pastel watercolor painting. zhuanchang"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"139:129": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx2.3-transition.safetensors",
"model": [
"139:127",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"139:143": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 6
},
"_meta": {
"title": "Duration"
}
},
"139:144": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a * b + 1",
"values.a": [
"139:143",
0
],
"values.b": [
"139:114",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"139:98": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1280
},
"_meta": {
"title": "Height"
}
},
"139:99": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"139:125",
0
],
"img_compression": 25
},
"_meta": {
"title": "LTXV Preprocess"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)問答
它會啟用模型 + LoRA 組合中的 ltx2.3-transition 行為。建議放在提示詞靠近結尾的位置,讓主體、場景、鏡頭與轉換細節仍然是主要描述;這有助於在套用轉換邏輯時保持基礎描述清楚。
用影格數與 FPS。相同 FPS 下,影格越多,轉換時間越長且更慢;影格越少則更快。你也可以在提示詞中加入時間語句(例如「前半段…接著…」),但主要仍由總影格數與播放速度決定。
當你想固定色盤、材質,或鎖定特定主體外觀時就用參考圖,並連到 pipeline 的 reference 輸入。若你想要純文字引導的轉換,可以略過參考,改用更具體的文字描述。
把 LoRA 強度降低到 0.4–0.6 以獲得較細微的變化,固定 seed 以便重現,並把提示詞簡化成更少但更清楚的視覺目標。避免互相衝突的描述;保持主體與鏡頭一致,只描述場景或風格如何演進。