Grille d'icônes de marque 3x3
Téléversez une image de référence d'une icône, entrez les informations de votre marque dans le prompt et générez 9 ressources d'icônes stylisées uniques de la marque.
À propos
Ce workflow ComfyUI, intitulé « Grille 3x3 d’icônes de marque », simplifie la création d’un ensemble d’icônes stylisées en accord avec l’identité de votre marque. En important une image de référence et en saisissant des informations spécifiques sur la marque, ce workflow génère neuf icônes uniques tout en maintenant la cohérence stylistique. Il utilise une combinaison de modèles et de nœuds, dont Gemini3 Pro Image Preview et Nano Banana Pro, pour garantir une sortie de haute qualité. Les nœuds clés comme LoadImage, GeminiImage2Node et SaveImage travaillent ensemble pour traiter l’image d’entrée et appliquer les transformations stylistiques souhaitées.
Techniquement, le workflow intègre des nœuds personnalisés comme comfyui-kjnodes et comfyui_essentials pour plus de flexibilité. Les nœuds PrimitiveInt et PrimitiveStringMultiline permettent des réglages précis, tandis que RegexReplace garantit que la sortie respecte les paramètres de marque. Les nœuds Reroute facilitent la circulation des données, assurant que chaque icône est générée avec les caractéristiques attendues. Ce workflow est particulièrement utile pour les designers et équipes marketing souhaitant produire rapidement un ensemble cohérent d’icônes sans sacrifier la créativité ou l’intégrité de la marque.
Ce que vous fournissez
- Lecture du workflow
S’exécute dans ComfyUI. Ce workflow ne peut pas s’exécuter sur cette page. Ouvrez-le dans Comfy Cloud, avec tout déjà chargé, ou téléchargez-le pour votre propre ComfyUI.
Essayer dans CloudDans le workflow
Un aperçu en lecture seule du graphe de nœuds. Ouvrez-le dans Comfy Cloud ou téléchargez-le pour modifier les nœuds.
Loading the graph
Open full-size workflow preview- Auteur
- Rob
Nécessite des nœuds personnalisés
- Lecture du workflow
Utiliser ce workflow depuis du code
Généré à partir du graphe et des entrées du workflow lorsque cela est possible ; sinon, les exemples enregistrés sont affichés. Vérifiez les identifiants et les points de terminaison avant d’exécuter le code, ce qui peut entraîner des frais.
What you need
- Runs on
- Comfy Cloud
- Clé
- COMFY_API_KEY
Nécessite un forfait Cloud payant et des crédits.
# 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({
"1": {
"class_type": "LoadImage",
"inputs": {
"image": "input_reference_icon.png"
},
"_meta": {
"title": "Load Reference Icon Image"
}
},
"3": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "1:1",
"images": [
"1",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"40",
0
],
"resolution": "4K",
"response_modalities": "IMAGE+TEXT",
"seed": 12345,
"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)"
}
},
"7": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-3x3_grid_icons",
"images": [
"3",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"8": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_1",
"images": [
"27:29",
0
]
},
"_meta": {
"title": "Save Image 1"
}
},
"9": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_2",
"images": [
"27:33",
0
]
},
"_meta": {
"title": "Save Image 2"
}
},
"10": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_3",
"images": [
"27:39",
0
]
},
"_meta": {
"title": "Save Image 3"
}
},
"11": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_5",
"images": [
"27:43",
0
]
},
"_meta": {
"title": "Save Image 5"
}
},
"12": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_6",
"images": [
"27:45",
0
]
},
"_meta": {
"title": "Save Image 6"
}
},
"13": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_7",
"images": [
"27:46",
0
]
},
"_meta": {
"title": "Save Image 7"
}
},
"14": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_8",
"images": [
"27:49",
0
]
},
"_meta": {
"title": "Save Image 8"
}
},
"24": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_9",
"images": [
"27:51",
0
]
},
"_meta": {
"title": "Save Image 9"
}
},
"25": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-icon_4",
"images": [
"27:40",
0
]
},
"_meta": {
"title": "Save Image 4"
}
},
"28": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 0
},
"_meta": {
"title": "Crop Inset Grid Images"
}
},
"39": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "A company building the operating system for Generative AI."
},
"_meta": {
"title": "Describe the Brand Context/Theme"
}
},
"40": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "{description}",
"replace": [
"39",
0
],
"string": [
"41",
0
]
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"41": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "Task: Generate a 3x3 grid containing 9 unique icons.\n\nStyle Source: Input Image (Crucial: maintain this exact perspective, dimensionality (e.g., isometric 3D, flat 2D), texture, lighting, and rendering style).\n\nContext & Content:\n{description}\n\nObjective: Create 9 distinct symbols that represent different facets, services, or themes related to the brand/aesthetic description above.\n\nTechnical Requirements & Process:\nStyle Replication: Analyze the input image's rendering style precisely. All output icons must adhere strictly to this aesthetic and perspective of the input image.\n\nUnique Generation: Develop 9 separate icon concepts based on the company focus. No two icons in the grid should be the same.\n\nGrid Layout: Arrange the 9 newly generated icons into a clean grid with 3 rows and 3 columns."
},
"_meta": {
"title": "Prompt Template"
}
},
"27:18": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"3",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"27:29": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:67",
0
],
"y": [
"27:71",
0
]
},
"_meta": {
"title": "1"
}
},
"27:32": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:29",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:33": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:59",
0
],
"y": [
"27:71",
0
]
},
"_meta": {
"title": "2"
}
},
"27:34": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:33",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:38": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:39",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:39": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:60",
0
],
"y": [
"27:71",
0
]
},
"_meta": {
"title": "3"
}
},
"27:40": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:67",
0
],
"y": [
"27:63",
0
]
},
"_meta": {
"title": "4"
}
},
"27:41": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:40",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:42": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:43",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:43": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:59",
0
],
"y": [
"27:63",
0
]
},
"_meta": {
"title": "5"
}
},
"27:44": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:45",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:45": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:60",
0
],
"y": [
"27:63",
0
]
},
"_meta": {
"title": "6"
}
},
"27:46": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:67",
0
],
"y": [
"27:62",
0
]
},
"_meta": {
"title": "7"
}
},
"27:47": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:46",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:48": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:49",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:49": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:59",
0
],
"y": [
"27:62",
0
]
},
"_meta": {
"title": "8"
}
},
"27:50": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:51",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:51": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"27:66",
0
],
"image": [
"3",
0
],
"width": [
"27:65",
0
],
"x": [
"27:60",
0
],
"y": [
"27:62",
0
]
},
"_meta": {
"title": "9"
}
},
"27:56": {
"class_type": "ImageBatchMulti",
"inputs": {
"image_1": [
"27:29",
0
],
"image_2": [
"27:33",
0
],
"image_3": [
"27:39",
0
],
"image_4": [
"27:40",
0
],
"image_5": [
"27:43",
0
],
"image_6": [
"27:45",
0
],
"image_7": [
"27:46",
0
],
"image_8": [
"27:49",
0
],
"image_9": [
"27:51",
0
],
"inputcount": 9
},
"_meta": {
"title": "Image Batch Multi"
}
},
"27:57": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"27:56",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"27:59": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"27:65",
0
],
"b": [
"27:64",
0
],
"value": "(a+b) + (b/2)"
},
"_meta": {
"title": "Col 2 - X val"
}
},
"27:60": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"27:65",
0
],
"b": [
"27:64",
0
],
"value": "(2*a) + (b*3)"
},
"_meta": {
"title": "Col 3 - X val"
}
},
"27:62": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"27:66",
0
],
"b": [
"27:64",
0
],
"value": "(2*a) + (3*b)"
},
"_meta": {
"title": "Row 3 - Y val"
}
},
"27:63": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"27:66",
0
],
"b": [
"27:64",
0
],
"value": "(a+b) + (b/2)"
},
"_meta": {
"title": "Row 2 - Y val"
}
},
"27:64": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"28",
0
],
"b": 0,
"value": "a"
},
"_meta": {
"title": "🔧 Simple Math"
}
},
"27:65": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"27:18",
0
],
"b": [
"27:64",
0
],
"value": "(a-3*b) / 3"
},
"_meta": {
"title": "WIDTH"
}
},
"27:66": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"27:18",
1
],
"b": [
"27:64",
0
],
"value": "(a-3*b) / 3"
},
"_meta": {
"title": "HEIGHT"
}
},
"27:67": {
"class_type": "SimpleMath+",
"inputs": {
"a": 0,
"b": [
"27:64",
0
],
"value": "b/2"
},
"_meta": {
"title": "Col 1 - X val"
}
},
"27:71": {
"class_type": "SimpleMath+",
"inputs": {
"a": 0,
"b": [
"27:64",
0
],
"value": "(b/2)"
},
"_meta": {
"title": "Row 1 - Y val"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)Questions-réponses
Oui, vous pouvez importer toute image comme référence, mais pour de meilleurs résultats, choisissez une image proche du style d’icône souhaité.
Ajustez les informations de marque et les préférences stylistiques dans les champs d’entrée pour mieux correspondre à votre palette de couleurs.
Le workflow utilise des modèles avancés comme Gemini3 Pro Image Preview pour garantir l’unicité de chaque icône tout en maintenant la cohérence stylistique.
Le workflow actuel est optimisé pour une grille 3x3. Pour plus d’icônes, relancez le workflow avec des paramètres différents.
Workflows associés
- Nano Banana Pro, Gemini3 Pro Image Preview, Google
Create a character turnaround
- Gemini3 Pro Image Preview, Nano Banana Pro, Google, ByteDance, Seedance
Ajouter texture et éléments à logo
- Gemini3 Pro Image Preview, Nano Banana Pro, Google, ByteDance, Seedance
Appliquer une texture au logo
- Gemini3 Pro Image Preview, Google, Nano Banana Pro
Changer le produit en main (style UGC)
- Gemini3 Pro Image Preview, Google, Nano Banana Pro
Colorer un dessin au trait
- Gemini3 Pro Image Preview, Google, Nano Banana Pro
Mannequin tenant le produit
- Kling, Google, Nano Banana Pro, Gemini3 Pro Image Preview
Message de Panneau d'Affichage LED
- Nano Banana Pro, Gemini3 Pro Image Preview, Google
Miniatures isométriques d'un selfie
- Gemini3 Pro Image Preview, Google, Nano Banana Pro
Nano Banana Pro
- Gemini3 Pro Image Preview, Google, Nano Banana Pro
Nano Banana Pro : Agrandissement créatif d'art stylisé
- Gemini3 Pro Image Preview, Nano Banana Pro, Google, ByteDance, Seedance
Remplacement produit pub
- Google Gemini Image, Nano Banana Pro, Google, Gemini3 Pro Image Preview
Selfie + Prompt textuel en gribouillage de séance photo studio