Planches d’animatique rapides
Itérez rapidement sur des planches animatiques ou des images clés à partir de votre propre art.
À propos
Animatic Boards Rapides est un workflow léger pour ComfyUI permettant de transformer rapidement vos croquis, beats ou vignettes en planches animatiques ou images clés 16:9 propres. Il standardise votre illustration dans un format adapté au storyboard, ajoute des notes de plan concises générées par un LLM, et permet de prévisualiser et d’exporter facilement. Chargez votre art via LoadImage, définissez une résolution cible avec PrimitiveNode (ex : 1920x1080), et itérez rapidement en prévisualisant dans PreviewAny avant d’enregistrer avec SaveImage.
Techniquement, le workflow fait passer votre image par un ensemble réduit de nœuds utilitaires personnalisés (IDs : d33c1791-dfd2-4102-8540-aa63e4434cd2, f2228dc9-64e8-43b1-a4ca-b8a57eed8f64, e3dd2fcb-0e5e-47a8-963b-adea96749eb0, 601fd020-3eba-4b24-b15f-a2a9c0307d3a, eaabb89a-2cd6-4960-ad44-1b152bff77c1, 86a340d1-ba23-44b6-8470-6b3d64167d65) qui gèrent la mise en page et la composition finale au format 16:9, avec des nœuds Reroute pour garder le graphe propre. GeminiNode est utilisé pour synthétiser ou affiner de brèves notes de plan à partir de votre prompt texte (et, si pris en charge, de l’image chargée). Les notes sont affichées dans PreviewAny pour être copiées dans vos documents de production ; certains layouts peuvent aussi afficher le texte sur l’image si cette branche est activée. Comme il n’utilise pas de sampler de diffusion, l’itération est rapide et prévisible—idéal pour le blocking de séquences ou la création d’images clés à partir de votre propre art.
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
- ComfyUI
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": "PreviewAny",
"inputs": {
"source": [
"2",
0
]
},
"_meta": {
"title": "Preview All Generated Prompts"
}
},
"2": {
"class_type": "GeminiNode",
"inputs": {
"images": [
"6",
0
],
"model": "gemini-3-pro-preview",
"prompt": "Generate 6 different prompts following the instructions below. \nEach prompt idea needs to be 50-80 words max and be separated by *.\nEach prompt should be unique, varying the camera angles and shot type. Add subtle detail and maintain consistent elements.",
"seed": 12345,
"system_prompt": ""
},
"_meta": {
"title": "Google Gemini"
}
},
"5": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_1",
"images": [
"10:69",
0
]
},
"_meta": {
"title": "Save Image 1"
}
},
"6": {
"class_type": "LoadImage",
"inputs": {
"image": "f076b4b3a7d2968cb0382a93479cf1e5af6117ccf4427bf131097b2daabfa6b4.png"
},
"_meta": {
"title": "Load Reference Image"
}
},
"11": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"10:67:64",
0
]
},
"_meta": {
"title": "Preview Prompt 1"
}
},
"18": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_2",
"images": [
"19:72",
0
]
},
"_meta": {
"title": "Save Image 1"
}
},
"20": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"19:70:80",
0
]
},
"_meta": {
"title": "Preview Prompt 2"
}
},
"21": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_3",
"images": [
"22:85",
0
]
},
"_meta": {
"title": "Save Image 3"
}
},
"23": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"22:83:93",
0
]
},
"_meta": {
"title": "Preview Prompt 3"
}
},
"24": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_4",
"images": [
"25:98",
0
]
},
"_meta": {
"title": "Save Image 4"
}
},
"26": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"25:96:113",
0
]
},
"_meta": {
"title": "Preview Prompt 4"
}
},
"27": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_5",
"images": [
"28:101",
0
]
},
"_meta": {
"title": "Save Image 5"
}
},
"29": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"28:99:121",
0
]
},
"_meta": {
"title": "Preview Prompt 5"
}
},
"30": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-image_6",
"images": [
"31:106",
0
]
},
"_meta": {
"title": "Save Image 6"
}
},
"32": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"31:104:129",
0
]
},
"_meta": {
"title": "Preview Prompt 6"
}
},
"10:67:3": {
"class_type": "SomethingToString",
"inputs": {
"input": [
"10:67:9",
0
],
"prefix": "",
"suffix": ""
},
"_meta": {
"title": "Something To String"
}
},
"10:67:62": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1
},
"_meta": {
"title": "Int - Select Prompt Number (not index)"
}
},
"10:67:64": {
"class_type": "RegexExtract",
"inputs": {
"case_insensitive": True,
"dotall": False,
"group_index": 1,
"mode": "First Group",
"multiline": True,
"regex_pattern": [
"10:67:8",
0
],
"string": [
"10:67:66",
0
]
},
"_meta": {
"title": "Extract Text"
}
},
"10:67:65": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"10:67:64",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"10:67:66": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": [
"2",
0
]
},
"_meta": {
"title": "Text (Multiline)"
}
},
"10:67:8": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "(?<=\\{)\\d+(?=\\})",
"replace": [
"10:67:3",
0
],
"string": "(?:^(?!\\s*\\*?\\s*$).+$\\n(?:^\\s*\\*?\\s*$\\n)*){0}^(?!\\s*\\*?\\s*$)(.+)$"
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"10:67:9": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"10:67:62",
0
],
"b": 0,
"value": "a-1"
},
"_meta": {
"title": "Convert Prompt Number to Index"
}
},
"10:68": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"6",
0
],
"images.image1": [
"10:69",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"10:69": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "16:9",
"images": [
"6",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"10:67:64",
0
],
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 1,
"system_prompt": "You are an expert image-generation engine. You must ALWAYS produce an image.\nInterpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.\nIf a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.\nPrioritize generating the visual representation above any text, formatting, or conversational requests."
},
"_meta": {
"title": "Nano Banana Pro (Google Gemini Image)"
}
},
"19:70:75": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "(?<=\\{)\\d+(?=\\})",
"replace": [
"19:70:78",
0
],
"string": "(?:^(?!\\s*\\*?\\s*$).+$\\n(?:^\\s*\\*?\\s*$\\n)*){0}^(?!\\s*\\*?\\s*$)(.+)$"
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"19:70:76": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 2
},
"_meta": {
"title": "Int - Select Prompt Number (not index)"
}
},
"19:70:77": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"19:70:76",
0
],
"b": 0,
"value": "a-1"
},
"_meta": {
"title": "Convert Prompt Number to Index"
}
},
"19:70:78": {
"class_type": "SomethingToString",
"inputs": {
"input": [
"19:70:77",
0
],
"prefix": "",
"suffix": ""
},
"_meta": {
"title": "Something To String"
}
},
"19:70:80": {
"class_type": "RegexExtract",
"inputs": {
"case_insensitive": True,
"dotall": False,
"group_index": 1,
"mode": "First Group",
"multiline": True,
"regex_pattern": [
"19:70:75",
0
],
"string": [
"19:70:82",
0
]
},
"_meta": {
"title": "Extract Text"
}
},
"19:70:81": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"19:70:80",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"19:70:82": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": [
"2",
0
]
},
"_meta": {
"title": "Text (Multiline)"
}
},
"19:71": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"6",
0
],
"images.image1": [
"19:72",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"19:72": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "16:9",
"images": [
"6",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"19:70:80",
0
],
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 2,
"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)"
}
},
"19:73": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"6",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"19:74": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"19:71",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"22:83:88": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "(?<=\\{)\\d+(?=\\})",
"replace": [
"22:83:91",
0
],
"string": "(?:^(?!\\s*\\*?\\s*$).+$\\n(?:^\\s*\\*?\\s*$\\n)*){0}^(?!\\s*\\*?\\s*$)(.+)$"
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"22:83:89": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 3
},
"_meta": {
"title": "Int - Select Prompt Number (not index)"
}
},
"22:83:90": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"22:83:89",
0
],
"b": 0,
"value": "a-1"
},
"_meta": {
"title": "Convert Prompt Number to Index"
}
},
"22:83:91": {
"class_type": "SomethingToString",
"inputs": {
"input": [
"22:83:90",
0
],
"prefix": "",
"suffix": ""
},
"_meta": {
"title": "Something To String"
}
},
"22:83:93": {
"class_type": "RegexExtract",
"inputs": {
"case_insensitive": True,
"dotall": False,
"group_index": 1,
"mode": "First Group",
"multiline": True,
"regex_pattern": [
"22:83:88",
0
],
"string": [
"22:83:95",
0
]
},
"_meta": {
"title": "Extract Text"
}
},
"22:83:94": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"22:83:93",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"22:83:95": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": [
"2",
0
]
},
"_meta": {
"title": "Text (Multiline)"
}
},
"22:84": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"6",
0
],
"images.image1": [
"22:85",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"22:85": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "16:9",
"images": [
"6",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"22:83:93",
0
],
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 3,
"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)"
}
},
"22:86": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"6",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"22:87": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"22:84",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"25:96:108": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "(?<=\\{)\\d+(?=\\})",
"replace": [
"25:96:111",
0
],
"string": "(?:^(?!\\s*\\*?\\s*$).+$\\n(?:^\\s*\\*?\\s*$\\n)*){0}^(?!\\s*\\*?\\s*$)(.+)$"
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"25:96:109": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 4
},
"_meta": {
"title": "Int - Select Prompt Number (not index)"
}
},
"25:96:110": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"25:96:109",
0
],
"b": 0,
"value": "a-1"
},
"_meta": {
"title": "Convert Prompt Number to Index"
}
},
"25:96:111": {
"class_type": "SomethingToString",
"inputs": {
"input": [
"25:96:110",
0
],
"prefix": "",
"suffix": ""
},
"_meta": {
"title": "Something To String"
}
},
"25:96:113": {
"class_type": "RegexExtract",
"inputs": {
"case_insensitive": True,
"dotall": False,
"group_index": 1,
"mode": "First Group",
"multiline": True,
"regex_pattern": [
"25:96:108",
0
],
"string": [
"25:96:115",
0
]
},
"_meta": {
"title": "Extract Text"
}
},
"25:96:114": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"25:96:113",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"25:96:115": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": [
"2",
0
]
},
"_meta": {
"title": "Text (Multiline)"
}
},
"25:97": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"6",
0
],
"images.image1": [
"25:98",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"25:98": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "16:9",
"images": [
"6",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"25:96:113",
0
],
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 4,
"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)"
}
},
"28:100": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"6",
0
],
"images.image1": [
"28:101",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"28:101": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "16:9",
"images": [
"6",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"28:99:121",
0
],
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 5,
"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)"
}
},
"28:102": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"6",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"28:103": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"28:100",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"28:99:116": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "(?<=\\{)\\d+(?=\\})",
"replace": [
"28:99:119",
0
],
"string": "(?:^(?!\\s*\\*?\\s*$).+$\\n(?:^\\s*\\*?\\s*$\\n)*){0}^(?!\\s*\\*?\\s*$)(.+)$"
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"28:99:117": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 5
},
"_meta": {
"title": "Int - Select Prompt Number (not index)"
}
},
"28:99:118": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"28:99:117",
0
],
"b": 0,
"value": "a-1"
},
"_meta": {
"title": "Convert Prompt Number to Index"
}
},
"28:99:119": {
"class_type": "SomethingToString",
"inputs": {
"input": [
"28:99:118",
0
],
"prefix": "",
"suffix": ""
},
"_meta": {
"title": "Something To String"
}
},
"28:99:121": {
"class_type": "RegexExtract",
"inputs": {
"case_insensitive": True,
"dotall": False,
"group_index": 1,
"mode": "First Group",
"multiline": True,
"regex_pattern": [
"28:99:116",
0
],
"string": [
"28:99:123",
0
]
},
"_meta": {
"title": "Extract Text"
}
},
"28:99:122": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"28:99:121",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"28:99:123": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": [
"2",
0
]
},
"_meta": {
"title": "Text (Multiline)"
}
},
"31:104:124": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "(?<=\\{)\\d+(?=\\})",
"replace": [
"31:104:127",
0
],
"string": "(?:^(?!\\s*\\*?\\s*$).+$\\n(?:^\\s*\\*?\\s*$\\n)*){0}^(?!\\s*\\*?\\s*$)(.+)$"
},
"_meta": {
"title": "Replace Text (Regex)"
}
},
"31:104:125": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 6
},
"_meta": {
"title": "Int - Select Prompt Number (not index)"
}
},
"31:104:126": {
"class_type": "SimpleMath+",
"inputs": {
"a": [
"31:104:125",
0
],
"b": 0,
"value": "a-1"
},
"_meta": {
"title": "Convert Prompt Number to Index"
}
},
"31:104:127": {
"class_type": "SomethingToString",
"inputs": {
"input": [
"31:104:126",
0
],
"prefix": "",
"suffix": ""
},
"_meta": {
"title": "Something To String"
}
},
"31:104:129": {
"class_type": "RegexExtract",
"inputs": {
"case_insensitive": True,
"dotall": False,
"group_index": 1,
"mode": "First Group",
"multiline": True,
"regex_pattern": [
"31:104:124",
0
],
"string": [
"31:104:131",
0
]
},
"_meta": {
"title": "Extract Text"
}
},
"31:104:130": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"31:104:129",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"31:104:131": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": [
"2",
0
]
},
"_meta": {
"title": "Text (Multiline)"
}
},
"31:105": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"6",
0
],
"images.image1": [
"31:106",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"31:106": {
"class_type": "GeminiImage2Node",
"inputs": {
"aspect_ratio": "16:9",
"images": [
"6",
0
],
"model": "gemini-3-pro-image-preview",
"prompt": [
"31:104:129",
0
],
"resolution": "2K",
"response_modalities": "IMAGE+TEXT",
"seed": 6,
"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)"
}
},
"31:107": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"31:105",
0
]
},
"_meta": {
"title": "Preview Image"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)Questions-réponses
Non. Ce workflow ne génère pas de nouvelles images. Il standardise votre art existant au format 16:9 et utilise GeminiNode pour produire des notes de plan optionnelles, ce qui rend l’itération rapide et cohérente.
Modifiez les valeurs de largeur et hauteur dans PrimitiveNode. Pour du 16:9, utilisez 1920x1080 ou 1280x720. Si vous changez de format, ajustez aussi les nœuds de layout ou de recadrage en aval.
Utilisez le modèle compatible avec votre Gemini node qui équilibre vitesse et qualité pour la génération de notes (par exemple, un modèle ‘Pro’ pour des notes plus riches ou ‘Lite’ pour plus de rapidité). Configurez-le dans GeminiNode avec votre clé API.
Ce modèle est conçu pour des images uniques à itération rapide. Pour traiter en lot, relancez le workflow avec différentes images ou ajoutez un loader d’images en lot relié au même layout et chemin de sauvegarde.