寫實海報重設計,角色形象煥新
將上傳圖片轉為逼真海報設計,在保持藝術風格與配色的同時改變人物姿勢、面部與服裝,輸出帶藝術字型、視覺衝擊力強的海報。
關於
這個 ComfyUI 工作流程「寫實海報重製與角色變身」可將上傳圖像轉換為寫實海報設計。運用 Nano Banana Pro 模型,能細緻變更角色姿勢、臉部與服裝,同時保留原圖的藝術風格與配色。流程以 LoadImage、SaveImage、GeminiImage2Node 等節點為主,協助完成轉換。ComfySwitchNode 與 StringConcatenate 節點可切換「海報重製模式」與「一般圖像編輯模式」,靈活調整轉換方式。
此流程特別適合藝術家與設計師,能創作具視覺衝擊力且帶有藝術字體的海報。結合 Nano Banana Pro 模型的能力,能產生美觀且技術精湛的成果。MarkdownNote 與 PrimitiveStringMultiline 節點可加入自訂文字與備註,讓流程更適合多元創意專案。
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
- ComfyUI
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({
"3": {
"class_type": "LoadImage",
"inputs": {
"image": "reference_poster.png"
},
"_meta": {
"title": "Load Image"
}
},
"4": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "Poster_maker",
"images": [
"25",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"25": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "auto",
"images": [
"3",
0
],
"model": "Nano Banana 2 (Gemini 3.1 Flash Image)",
"prompt": [
"26",
0
],
"resolution": "2K",
"response_modalities": "IMAGE",
"seed": 935249916317050,
"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)"
}
},
"26": {
"class_type": "ComfySwitchNode",
"inputs": {
"on_false": [
"27",
0
],
"on_true": [
"28",
0
],
"switch": False
},
"_meta": {
"title": "If/Else Switch"
}
},
"27": {
"class_type": "StringConcatenate",
"inputs": {
"delimiter": "",
"string_a": "You are a master poster designer. Refer to the style, color and font style of the pictures I uploaded, and transform them into a realistic real person style to design a poster with visual impact and artistry. Change the posture, face and clothing of the character. The main title font should be artistic, mainly white and large, and try not to cover the character's face. Without referring to the watermark LOGO and the tiny text, the following is the content of the poster:",
"string_b": [
"28",
0
]
},
"_meta": {
"title": "Concatenate Text"
}
},
"28": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "Imitate any style, \nrecreate any poster."
},
"_meta": {
"title": "Prompt"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)問答
目前流程設計為單張圖像轉換。需逐張載入與處理。
建議選用角色特徵明顯、配色清楚的圖像,模型較能精確變更並保留藝術感。
請用 ComfySwitchNode 切換模式。「海報重製模式」可輸入海報內容,一般編輯則直接處理圖像。
可以,請用 MarkdownNote 與 PrimitiveStringMultiline 節點新增與調整文字內容。