AI on the Lot 2026 - LTX-2.3 - i2v
AI on the Lot 2026 第五個釋出的工作流程,提供 ComfyUI 101 工作坊學員開啟與跟隨。此為基於 LTX 2.3 模型的圖像轉影片流程,將靜態圖像轉為生成影片片段。
關於
這個 ComfyUI 工作流程利用 Lightricks 的 LTX‑2.3 影像轉影片模型,將單張靜態圖片轉換為短動畫影片。流程簡單明瞭:LoadImage 將你的來源影像載入圖中,自訂的 LTX‑2.3 節點(2454ad83-157c-40dd-9f19-5daaf4041ce0)根據該圖片與文字提示生成動作,最後 SaveVideo 將產生的影格組合成可播放的影片。圖中的 MarkdownNote 節點提供操作指引與提示詞建議,方便你在 AI on the Lot 2026 ComfyUI 101 工作坊過程中參考。
技術上,LTX‑2.3 節點會將你的輸入圖片編碼到模型的潛在空間,並根據你的提示詞生成時序連貫的影格序列。你可以透過描述「核心動作」與指定想保留的具體「視覺細節」來控制動作的內容與節奏,這也是 LTX‑2.3 提示詞建議中的推薦做法。該節點通常會開放文字提示詞、重現用的種子、影格數量和/或 FPS 等參數(實際參數依節點版本而異)。SaveVideo 會依你選擇的影格率將影格寫入磁碟。模型權重請使用 Lightricks/LTX‑2.3(可於 Hugging Face 取得,詳見連結),並依節點的 loader 欄位指定正確檔案位置。
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。
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({
"75": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/LTX_2.3_i2v",
"format": "auto",
"format.codec": "auto",
"video": [
"320:310",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"269": {
"class_type": "LoadImage",
"inputs": {
"image": "92a9314e31dced3cd7c657effe9240281caf8802bf430d699574869bb15dc58f.png"
},
"_meta": {
"title": "Load Image"
}
},
"320:276": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 42
},
"_meta": {
"title": "RandomNoise"
}
},
"320:277": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 1107858748962189
},
"_meta": {
"title": "RandomNoise"
}
},
"320:278": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"320:307",
1
],
"video_latent": [
"320:288",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"320:279": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-distilled-fp8.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"320:280": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_cfg_pp"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"320:281": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "0.85, 0.7250, 0.4219, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"320:282": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"320:285",
0
],
"negative": [
"320:284",
1
],
"positive": [
"320:284",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"320:283": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"320:314",
0
],
"latent_image": [
"320:318",
0
],
"noise": [
"320:277",
0
],
"sampler": [
"320:291",
0
],
"sigmas": [
"320:306",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"320:284": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"320:307",
0
],
"negative": [
"320:304",
1
],
"positive": [
"320:304",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"320:285": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2.3-22b-distilled-lora-384-1.1.safetensors",
"model": [
"320:316",
0
],
"strength_model": 0.5
},
"_meta": {
"title": "Load LoRA"
}
},
"320:286": {
"class_type": "ResizeImagesByLongerEdge",
"inputs": {
"images": [
"320:290",
0
],
"longer_edge": 1536
},
"_meta": {
"title": "Resize Images by Longer Edge (DEPRECATED)"
}
},
"320:287": {
"class_type": "LTXVLatentUpsampler",
"inputs": {
"samples": [
"320:307",
0
],
"upscale_model": [
"320:311",
0
],
"vae": [
"320:316",
2
]
},
"_meta": {
"title": "LTXVLatentUpsampler"
}
},
"320:288": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"320:302",
0
],
"image": [
"320:289",
0
],
"latent": [
"320:287",
0
],
"strength": 1,
"vae": [
"320:316",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"320:289": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"320:286",
0
],
"img_compression": 18
},
"_meta": {
"title": "LTXV Preprocess"
}
},
"320:290": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"269",
0
],
"resize_type": "scale dimensions",
"resize_type.crop": "center",
"resize_type.height": [
"320:299",
0
],
"resize_type.width": [
"320:312",
0
],
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"320:291": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_ancestral_cfg_pp"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"320:292": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"320:312",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"320:294": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a/2",
"values.a": [
"320:299",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"320:295": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"320:294",
1
],
"length": [
"320:323",
1
],
"width": [
"320:292",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"320:296": {
"class_type": "LTXVImgToVideoInplace",
"inputs": {
"bypass": [
"320:302",
0
],
"image": [
"320:289",
0
],
"latent": [
"320:295",
0
],
"strength": 0.7,
"vae": [
"320:316",
2
]
},
"_meta": {
"title": "LTXVImgToVideoInplace"
}
},
"320:297": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"320:279",
0
],
"samples": [
"320:309",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"320:298": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a",
"values.a": [
"320:300",
0
]
},
"_meta": {
"title": "Math Expression"
}
},
"320:299": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1024
},
"_meta": {
"title": "Height"
}
},
"320:300": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 25
},
"_meta": {
"title": "Frame Rate"
}
},
"320:301": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 5
},
"_meta": {
"title": "Duration"
}
},
"320:302": {
"class_type": "PrimitiveBoolean",
"inputs": {
"value": False
},
"_meta": {
"title": "Switch to Text to Video?"
}
},
"320:303": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"320:317",
0
],
"text": [
"320:319",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"320:304": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"320:298",
0
],
"negative": [
"320:313",
0
],
"positive": [
"320:303",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"320:305": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"320:279",
0
],
"batch_size": 1,
"frame_rate": [
"320:298",
1
],
"frames_number": [
"320:323",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"320:306": {
"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"
}
},
"320:307": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"320:283",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"320:308": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"320:282",
0
],
"latent_image": [
"320:278",
0
],
"noise": [
"320:276",
0
],
"sampler": [
"320:280",
0
],
"sigmas": [
"320:281",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"320:309": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"320:308",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"320:310": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"320:297",
0
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"320:298",
0
],
"images": [
"320:315",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"320:311": {
"class_type": "LatentUpscaleModelLoader",
"inputs": {
"model_name": "ltx-2.3-spatial-upscaler-x2-1.1.safetensors"
},
"_meta": {
"title": "Load Latent Upscale Model"
}
},
"320:312": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1024
},
"_meta": {
"title": "Width"
}
},
"320:313": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"320:317",
0
],
"text": "pc game, console game, video game, cartoon, childish, ugly"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"320:314": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"320:285",
0
],
"negative": [
"320:304",
1
],
"positive": [
"320:304",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"320:315": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"samples": [
"320:309",
0
],
"temporal_overlap": 4,
"temporal_size": 4096,
"tile_size": 768,
"vae": [
"320:316",
2
]
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"320:316": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2.3-22b-distilled-fp8.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"320:317": {
"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"
}
},
"320:318": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"320:305",
0
],
"video_latent": [
"320:296",
0
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"320:319": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "Static medium close-up of the man, framing locked, no camera movement. He looks directly at camera and says, in a low, gravelly, weathered voice: \"Enjoy the workshop at A.I. on the Lot, twenty twenty-six.\" Natural mouth movement matching the dialogue, subtle micro-expressions, eyes steady on lens. Smoke continues to drift across frame from camera right, curling and dissipating. A few wisps of hair shift slightly in the warm breeze. No head turn, no body movement, no eye darting, no other people, no sudden gestures."
},
"_meta": {
"title": "Prompt"
}
},
"320:323": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a * b + 1",
"values.a": [
"320:301",
0
],
"values.b": [
"320:300",
0
]
},
"_meta": {
"title": "Math Expression (length)"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)問答
描述「核心動作」隨時間展開(如「鏡頭慢慢推近,前景落葉飄過」),並列出需保留的「視覺細節」(如構圖、燈光、色彩、主體特徵)。指令要簡潔明確。
乾淨、光線充足且主體分離明確的圖像較易產生連貫動畫。解析度請依 VRAM 與流程預設,長寬比輸入輸出一致可避免拉伸。
長度由生成畫格數與 SaveVideo FPS 決定。增加畫格數可延長影片,調整 FPS 改變播放感。若 LTX‑2.3 節點有畫格數或長度設定,請於該處調整,再於 SaveVideo 設定 FPS。
請於 LTX‑2.3 節點(若有)設定並重複使用同一種子,保持提示詞與其他參數不變。變更種子可用於探索不同變化。