Selfie + Prompt textuel en gribouillage de séance photo studio
Téléversez un selfie et décrivez votre tenue dans le prompt. Générez 4 photographies éditoriales de mode avec des illustrations de doodles amusantes. Sélectionnez l'image à agrandir et à ajouter des détails du visage.
À propos
Ce workflow ComfyUI transforme un simple selfie en photo éditoriale de mode avec des illustrations doodle créatives. En combinant des modèles IA avancés comme Google Gemini Image et Nano Banana Pro, l’utilisateur importe un selfie et une invite texte décrivant la tenue souhaitée. Le processus génère quatre photos de mode distinctes, chacune enrichie de doodles artistiques pour une touche unique. Le workflow est à la fois convivial et techniquement robuste, utilisant des nœuds comme LoadImage pour l’import du selfie et RegexReplace pour le traitement de l’invite. Le nœud GeminiImage2Node synthétise les images initiales, tandis que les nœuds ImageBatch et ImageFromBatch facilitent la création et la sélection de plusieurs sorties. L’utilisateur peut ensuite upscaler l’image choisie et affiner les détails du visage pour un rendu final soigné.
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
- Vos fichiers
- Importés par le code depuis leurs URL
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": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Load Subject Image"
}
},
"4": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "a high neckline ribbed white tank top and baggy fitting loose faded denim jeans, with black high heel shoes"
},
"_meta": {
"title": "Describe the Subject's Outfit"
}
},
"5": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "A 2x2 (2 rows, 2 cols) grid of high fashion photoshoot images of the model wearing {outfit}, each grid image should show the a full body shot of the subject in slightly different poses.\n\nDO NOT generate the grid with any visible borders or gutters.\n\nThe setting is a studio environment with a white background. \n\nThe image is shot on fuji velvia film on a 55mm prime lens with a hard flash, the light is concentrated on the subject."
},
"_meta": {
"title": "Prompt Template"
}
},
"6": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "{outfit}",
"replace": [
"4",
0
],
"string": [
"5",
0
]
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"8": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_stitched",
"images": [
"9",
0
]
},
"_meta": {
"title": "Save Stitched Image"
}
},
"9": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "auto",
"images": [
"1",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"6",
0
],
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 111,
"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)"
}
},
"10": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 0
},
"_meta": {
"title": "Crop Inset Grid Images"
}
},
"12": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_1",
"images": [
"11:8",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"13": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_2",
"images": [
"11:9",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"14": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_3",
"images": [
"11:10",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"15": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_4",
"images": [
"11:11",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"16": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "auto",
"images": [
"9",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": "Apply playful hand-drawn doodles and bold brush strokes in a colorful assortment of colors. The doodles are messy yet graphic and stylish, editorial magazine vibe. Do not distort the subject.",
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 222,
"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)"
}
},
"17": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_stitched_doodles",
"images": [
"16",
0
]
},
"_meta": {
"title": "Save Stitched Doodled Image"
}
},
"20": {
"class_type": "ImageBatch",
"inputs": {
"image1": [
"23",
0
],
"image2": [
"1",
0
]
},
"_meta": {
"title": "Batch Images (DEPRECATED)"
}
},
"23": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": 3,
"image": [
"11:20",
0
],
"length": 1
},
"_meta": {
"title": "Select Image to Upscale"
}
},
"25": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "auto",
"images": [
"20",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": "Upscale image 1 and add subtle details. Use the face from image 2 to add back facial consistency. Maintain the colors of the doodle illustrations.",
"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)"
}
},
"26": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_upscaled",
"images": [
"25",
0
]
},
"_meta": {
"title": "Save Upscaled Image"
}
},
"27": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"23",
0
]
},
"_meta": {
"title": "Preview Selected Image"
}
},
"11:10": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"11:16",
0
],
"image": [
"16",
0
],
"width": [
"11:15",
0
],
"x": [
"11:24",
0
],
"y": [
"11:12",
0
]
},
"_meta": {
"title": "3"
}
},
"11:11": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"11:16",
0
],
"image": [
"16",
0
],
"width": [
"11:15",
0
],
"x": [
"11:13",
0
],
"y": [
"11:12",
0
]
},
"_meta": {
"title": "4"
}
},
"11:12": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"11:16",
0
],
"b": [
"11:14",
0
],
"value": "a + (b/2)"
},
"_meta": {
"title": "Row 2 - Y val"
}
},
"11:13": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"11:15",
0
],
"b": [
"11:14",
0
],
"value": "a + (b/2)"
},
"_meta": {
"title": "Col 2 - X val"
}
},
"11:14": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"10",
0
],
"b": 0,
"value": "a"
},
"_meta": {
"title": "🔧 Simple Math"
}
},
"11:15": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"11:17",
0
],
"b": [
"11:14",
0
],
"value": "(a-2*b) / 2"
},
"_meta": {
"title": "WIDTH"
}
},
"11:16": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"11:17",
1
],
"b": [
"11:14",
0
],
"value": "(a-2*b) / 2"
},
"_meta": {
"title": "HEIGHT"
}
},
"11:17": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"16",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"11:19": {
"class_type": "ImageBatchMulti",
"inputs": {
"image_1": [
"11:8",
0
],
"image_2": [
"11:9",
0
],
"image_3": [
"11:10",
0
],
"image_4": [
"11:11",
0
],
"inputcount": 4
},
"_meta": {
"title": "Image Batch Multi"
}
},
"11:20": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 2,
"height": [
"11:22",
0
],
"image": [
"11:19",
0
],
"keep_proportion": "stretch",
"pad_color": "0, 0, 0",
"upscale_method": "nearest-exact",
"width": [
"11:23",
0
]
},
"_meta": {
"title": "Resize Images"
}
},
"11:21": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"11:20",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"11:22": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"11:17",
1
],
"b": 0,
"value": "(a) / 2"
},
"_meta": {
"title": "HEIGHT / 2"
}
},
"11:23": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"11:17",
0
],
"b": 0,
"value": "(a) / 2"
},
"_meta": {
"title": "WIDTH / 2"
}
},
"11:24": {
"class_type": "SimpleMath+",
"inputs": {
"a": 0,
"b": [
"11:14",
0
],
"value": "b/2"
},
"_meta": {
"title": "Col 1 - X val"
}
},
"11:4": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"11:8",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"11:5": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"11:9",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"11:6": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"11:10",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"11:7": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"11:11",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"11:8": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"11:16",
0
],
"image": [
"16",
0
],
"width": [
"11:15",
0
],
"x": [
"11:24",
0
],
"y": [
"11:24",
0
]
},
"_meta": {
"title": "1"
}
},
"11:9": {
"class_type": "ImageCrop",
"inputs": {
"height": [
"11:16",
0
],
"image": [
"16",
0
],
"width": [
"11:15",
0
],
"x": [
"11:13",
0
],
"y": 0
},
"_meta": {
"title": "2"
}
}
})
# Replace each example.com URL with a public URL of your file.
workflow.set_input("1", "image", client.assets.from_url("https://example.com/replace-with-a-url/image"))
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)Questions-réponses
Oui, mais pour de meilleurs résultats, privilégiez une image claire et bien éclairée.
Utilisez le paramètre batch_index pour sélectionner l’image souhaitée. La première image correspond à l’index 0.
Affinez votre invite texte pour des illustrations plus précises. Le nœud RegexReplace peut aider à ajuster l’invite.
Actuellement, le workflow ne permet pas l’édition post-génération des doodles. Modifiez l’invite initiale pour obtenir d’autres résultats.