為 logo 新增紋理元素
上傳你的 logo、紋理和元素。產生一個品牌化紋理 logo 的影片素材。
關於
此 ComfyUI 工作流程可將靜態 Logo 轉換為動態、帶有材質效果的影片資產,非常適合提升品牌形象。流程結合多個專用節點與模型,讓使用者上傳 Logo、材質與元素,並將這些素材整合成一支影片。流程從『LoadImage』節點開始,將 Logo、材質與其他元素匯入。接著『GeminiImage2Node』處理這些圖像,將指定材質與元素套用至 Logo,並利用 Gemini3 Pro Image Preview 模型確保高品質圖像處理。
圖像處理完成後,『ByteDanceImageToVideoNode』將帶材質的 Logo 轉換為影片格式,運用 ByteDance 模型的先進技術確保轉場流暢且專業。最後,『SaveVideo』節點輸出完成影片,可直接用於品牌行銷素材。若需靜態圖像,也可用『SaveImage』節點擷取影片畫面。此流程特別適合品牌設計師快速製作吸睛視覺內容,無需繁複影片編輯技能。
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- 作者
- Rob
需要自訂節點
- 正在讀取工作流程
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({
"4": {
"class_type": "LoadImage",
"inputs": {
"button": {
"clicked": False,
"computedDisabled": False,
"computedHeight": 24,
"label": "choose file to upload",
"last_y": 70,
"name": "upload",
"options": {
"canvasOnly": True,
"serialize": False
},
"type": "button",
"y": 70
},
"image": "de8196b2e4887c7e987d9940dbd4c886bbdab2a04bea3187590426e237408fac.png"
},
"_meta": {
"title": "Load Logo Image"
}
},
"7": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "1:1",
"images": [
"21:27",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": "Apply the texture and background from image 2 into the logo from image 1. The logotype is in a 3d setting, match the lighting from the matcap. Use the elements from image 3, duplicate and apply them in multiple sizes and positions, scattered throughout the 3d environment creating a sense of depth and playful composition",
"resolution": "1K",
"response_modalities": "IMAGE+TEXT",
"seed": 495849069868986,
"system_prompt": "You are an expert image-generation engine. You must ALWAYS produce an image.\nInterpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.\nIf a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.\nPrioritize generating the visual representation above any text, formatting, or conversational requests."
},
"_meta": {
"title": "Nano Banana Pro (Google Gemini Image)"
}
},
"11": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"24",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"13": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI",
"images": [
"7",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"17": {
"class_type": "LoadImage",
"inputs": {
"button": {
"clicked": False,
"computedDisabled": False,
"computedHeight": 24,
"label": "choose file to upload",
"last_y": 70,
"name": "upload",
"options": {
"canvasOnly": True,
"serialize": False
},
"type": "button",
"y": 70
},
"image": "de8196b2e4887c7e987d9940dbd4c886bbdab2a04bea3187590426e237408fac.png"
},
"_meta": {
"title": "Load Texture Image"
}
},
"18": {
"class_type": "LoadImage",
"inputs": {
"button": {
"clicked": False,
"computedDisabled": False,
"computedHeight": 24,
"label": "choose file to upload",
"last_y": 70,
"name": "upload",
"options": {
"canvasOnly": True,
"serialize": False
},
"type": "button",
"y": 70
},
"image": "de8196b2e4887c7e987d9940dbd4c886bbdab2a04bea3187590426e237408fac.png"
},
"_meta": {
"title": "Load Elements Image"
}
},
"24": {
"class_type": "ByteDanceImageToVideoNode",
"inputs": {
"aspect_ratio": "adaptive",
"camera_fixed": True,
"duration": 5,
"generate_audio": False,
"image": [
"7",
0
],
"model": "seedance-1-0-pro-250528",
"prompt": "A floating logo wordmark playfully animates. The logo has a fluffy texture. The camera remains static, focusing on the elements in the scene animate individually and float making distinctly subtle but fun movements",
"resolution": "1080p",
"seed": 125213764,
"watermark": False
},
"_meta": {
"title": "ByteDance Image to Video"
}
},
"21:15": {
"class_type": "ResizeAndPadImage",
"inputs": {
"image": [
"17",
0
],
"interpolation": "area",
"padding_color": "white",
"target_height": [
"21:16",
1
],
"target_width": [
"21:16",
0
]
},
"_meta": {
"title": "Resize And Pad Image"
}
},
"21:16": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"4",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"21:20": {
"class_type": "ResizeAndPadImage",
"inputs": {
"image": [
"18",
0
],
"interpolation": "area",
"padding_color": "white",
"target_height": [
"21:16",
1
],
"target_width": [
"21:16",
0
]
},
"_meta": {
"title": "Resize And Pad Image"
}
},
"21:27": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"4",
0
],
"images.image1": [
"21:15",
0
],
"images.image2": [
"21:20",
0
]
},
"_meta": {
"title": "Batch Images"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)問答
可以。只要上傳為相容的圖片格式,工作流程即可用於任何 logo。
最終影片通常以 MP4 格式儲存,且在各平台都有廣泛支援。
不需要。此工作流程以易用與直覺為設計,即使新手也能使用。
請確保輸入圖片(logo、材質、元素)具有高解析度,並使用「Gemini3 Pro Image Preview」模型在儲存前檢視品質。