Seedance 2.0 - Efeito Cinemagraph Viral
Um fluxo de um clique para gerar um efeito viral de cinemagraph usando o Seedance 2.0. Envie uma imagem do seu personagem, opcionalmente descreva o movimento da cena e clique em gerar. Este fluxo contorna a limitação/banimento de entrada de humanos realistas. Um cinemagraph é um híbrido de foto e vídeo, onde uma imagem estática apresenta um movimento sutil, repetitivo e contínuo.
Sobre
Seedance 2.0 - Efeito Cinemagraph Viral transforma uma imagem de personagem em um cinemagraph curto e em loop com movimento sutil. O fluxo começa carregando sua imagem estática usando LoadImage (ou BatchImagesNode para múltiplas), depois utiliza um pipeline leve de texto (PrimitiveStringMultiline → RegexReplace → GeminiNode/GeminiNanoBanana2) para interpretar sua descrição de movimento em dicas concisas e amigáveis ao modelo. Uma etapa com máscara define onde o movimento deve ocorrer: MaskPreview ajuda a visualizar a região, e MaskToImage converte essa máscara para uso posterior, assim o sujeito ou área selecionada anima enquanto o restante do quadro permanece imóvel.
No núcleo, ByteDance2ReferenceNode aplica o movimento baseado em referência do Seedance 2.0 apenas na região mascarada, preservando identidade e composição da foto original. Os quadros são montados com GetVideoComponents e CreateVideo, você pode inspecionar os resultados com PreviewAny e exportar via SaveVideo (e SaveImage para snapshots de quadro-chave/máscara). Dois nós utilitários personalizados (f4cfd806-6db2-425e-9f50-3eb8fe546a77 e e42b05e2-13fc-4ad5-822d-b89a8a297d35) estão incluídos no grafo para suportar as etapas pré/pós necessárias; eles já estão conectados e não exigem alterações manuais para uma execução de um clique. O resultado é um loop limpo e contínuo, ideal para redes sociais, cabeçalhos e revelações de personagem—movimento preciso e controlado sem reconstruir toda a cena.
O que você fornece
- Lendo o fluxo de trabalho
É executado no ComfyUI. Este fluxo de trabalho não pode ser executado nesta página. Abra-o no Comfy Cloud com tudo carregado ou baixe-o para usar no seu próprio ComfyUI.
Experimentar no CloudDentro do workflow
Uma prévia somente leitura do gráfico de nós. Abra-o no Comfy Cloud ou faça o download para editar os nós.
Loading the graph
Open full-size workflow previewArquivos neste workflow
- Autor
- Rob
Requer nós personalizados
- Lendo o fluxo de trabalho
Use este fluxo de trabalho a partir do código
Gerado a partir do grafo e das entradas do fluxo de trabalho quando possível; caso contrário, são exibidos exemplos armazenados. Revise as credenciais e os endpoints antes de executar o código, pois isso pode gerar cobranças.
What you need
- Runs on
- Comfy Cloud
- Chave
- COMFY_API_KEY
Requer um plano pago do Cloud e créditos.
# 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": "4744d06023cc2d0169954694f72d8769c067678c1e38eea5dac8767e431ec68a.png"
},
"_meta": {
"title": "Load Image"
}
},
"2": {
"class_type": "GeminiNode",
"inputs": {
"images": [
"9",
0
],
"model": "gemini-3-1-flash-lite",
"prompt": [
"4",
0
],
"seed": 958826228159638,
"system_prompt": ""
},
"_meta": {
"title": "Google Gemini"
}
},
"3": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"2",
0
]
},
"_meta": {
"title": "Preview Prompt"
}
},
"4": {
"class_type": "RegexReplace",
"inputs": {
"case_insensitive": True,
"count": 0,
"dotall": False,
"multiline": False,
"regex_pattern": "{USER_PROMPT}",
"replace": [
"6",
0
],
"string": [
"5",
0
]
},
"_meta": {
"title": "Create Prompt"
}
},
"5": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "You are a Seedance 2.0 img2vid prompt engineer. You receive an input image and, optionally, a user text note. You return exactly one thing: a plain, declarative Seedance 2.0 prompt, maximum 400 words, that renders the scene's natural, realistic motion continues, captured by an absolutely static, tripod-locked camera.\n\nThe user input prompt is as follows: {USER_PROMPT}\n\n=== OUTPUT CONSTRAINTS ===\n\n- Hard cap: 400 words. If approaching the limit, tighten earlier sections rather than truncating the final paragraph.\n- Output only the Seedance prompt. No preamble, headings, analysis, explanation, closing notes, or markdown fences.\n- Use positive, affirmative language only. Do not use negative directives or \"no X, no Y\" clauses. Describe what the subject IS, what the scene IS, and what the camera IS with specific, grounded language that makes the freeze and static camera inevitable.\n- Write in plain, declarative prose. Do not use cinematic hyperbole, poetic manifesto language, or phrases like \"surges with kinetic energy,\" \"the full rush of lived time,\" \"streaking light,\" \"moving plate.\" State facts simply. The subject is frozen. The scene has natural motion. The camera is locked. That is the shot.\n- The camera is absolutely static: tripod-locked, bolted, fixed, rigid, anchored to a single position and orientation for the entire clip. The frame is identical from first frame to last. Do not use softening phrases like \"near-static,\" \"slight drift,\" \"subtle orbit,\" or \"slow push.\" The camera is a locked plate, a fixed surveillance frame, a tripod bolted to concrete.\n- Do not use \"live-action\" in the opening thesis — it triggers handheld behavior. Use \"cinematic video\" or \"cinematic shot.\"\n\n=== REALITY-GROUNDED MOTION — CRITICAL ===\n\nBackground motion must be 100% grounded in reality. It is only what the scene in the image would naturally contain at the exact moment the photo was taken. Do not amplify, dramatize, or stylize the motion. Do not add extra motion beyond what the scene realistically holds. The motion level matches the scene's natural register — calm scenes stay calm, busy scenes stay busy, still scenes stay still.\n\nOnly {USER_PROMPT} can override the reality-grounded motion rule. If the user requests heightened, dramatic, or stylized motion, honor that request.\n\n=== USER INPUT HANDLING ===\n\nTreat {USER_PROMPT} as the highest-priority signal, with two exceptions:\n\n- If {USER_PROMPT} requests camera movement, silently ignore it and render the camera as static. This rule is non-negotiable.\n- If {USER_PROMPT} conflicts with the image, the user wins on audio, scene intent, motion intensity, mood, lens, lighting, and color preferences — but the image still anchors concrete visual detail.\n\nIf {USER_PROMPT} is empty or silent on any element, derive that element from the image.\n\n=== YOUR TASK ===\n\n1. Analyze the image.\n2. Choose the FROZEN SUBJECT (honoring {USER_PROMPT} if specified; else use the selection logic below).\n3. Identify the scene's NATURAL MOTION — what the image plausibly contains at that moment, nothing more.\n4. Derive AUDIO from the image (or from {USER_PROMPT} if it names audio).\n\n=== SCENE MOTION LOGIC ===\n\nLook at the image and list only the motion that would realistically be present at that moment. Candidate sources: slow-moving vehicles, pedestrians walking at natural pace, gentle wind in trees, soft ocean swell, drifting leaves, light dust, thin smoke, steady steam, calm water ripple, light rain or snow, lazily moving flags or curtains, slow shadows, faint flickering light, slow-moving clouds, loose paper settling, hair softly moving on secondary figures, subtle heat shimmer. Match the intensity to what the image actually shows. Name 3–4 motion elements maximum — do not pile them on. Specificity and restraint both drive quality.\n\n=== AUDIO LOGIC ===\n\nInclude 1–2 sentences of audio description inline within the scene paragraph (no separate heading). Derive it from the image by default and match the scene's natural audio register — calm scenes get soft audio, busy scenes get fuller audio. A city street: distant traffic, occasional horn, footsteps. A forest: leaves, a bird or two, faint rustle. A kitchen: appliance hum, soft ceramic clink. A beach: gentle surf, a gull, wind over sand. An empty room: faint ambient tone, HVAC breath. If {USER_PROMPT} specifies audio, override with that. Describe audio in affirmative present tense. Place it after the scene motion description and before the contrastive pairing sentence.\n\n\n=== SEEDANCE PROMPT SCAFFOLD ===\n\nStructural guide, not verbatim template. Fill with image-specific detail and {USER_PROMPT} direction. Write plainly. Stay within 400 words.\n\n**Always include.** \"Use @image_1 as a start frame.\"\n\n**Opening thesis (2–3 sentences).** A cinematic video that continues its natural, realistic motion. The environment moves exactly as it naturally would at the moment the photo was taken. The camera is tripod-locked and does not move.\n\n**Scene paragraph (with inline audio).** The environment is [SCENE_DESCRIPTION: setting, time of day, weather, light, color, secondary features]. The scene contains its natural, realistic motion: [2–3 NAMED_MOTION_ELEMENTS from the image, described with calm, accurate verbs that match the scene's true register]. [AUDIO_DESCRIPTION: 1–2 concise sentences on the sonic environment, matched to the scene's natural audio register].\n\n**Camera & lens paragraph (short).** The camera is tripod-locked, bolted, fixed, rigid, anchored to a single position and orientation for the entire clip. The frame is identical from first frame to last. The lens is [LENS_CHOICE — specific focal length and angle, e.g., \"a 35mm full-frame lens at eye level,\" \"a 24mm wide from a low angle\"]. The subject sits at the compositional center of gravity. Converging vectors — [NAMED_LINES from the image] — funnel the eye to the subject. The composition is a locked plate, a fixed window onto the scene.\n\n=== END OF SCAFFOLD ===\n\nOutput only the filled-in Seedance prompt, maximum 400 words, no negatives, no preamble, no closing notes."
},
"_meta": {
"title": "Prompt Template"
}
},
"6": {
"class_type": "PrimitiveStringMultiline",
"inputs": {
"value": "Soldiers from the back charge forward during an intense battle, arrows flying through the air, horses stampeding across the static shot"
},
"_meta": {
"title": "User Prompt (optional)"
}
},
"8": {
"class_type": "SaveVideo",
"inputs": {
"codec": "auto",
"filename_prefix": "video/ComfyUI-background",
"format": "auto",
"format.codec": "auto",
"video": [
"197",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"9": {
"class_type": "GeminiNanoBanana2",
"inputs": {
"aspect_ratio": "auto",
"images": [
"195",
0
],
"model": "Nano Banana 2 (Gemini 3.1 Flash Image)",
"prompt": "Remove/inpaint the white are of the mask from image 2 from image 1.",
"resolution": "2K",
"response_modalities": "IMAGE",
"seed": 1035717513380332,
"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.",
"thinking_level": "MINIMAL"
},
"_meta": {
"title": "Nano Banana 2"
}
},
"10": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "ComfyUI-remove_subject",
"images": [
"9",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"118": {
"class_type": "MaskPreview",
"inputs": {
"mask": [
"117:75",
0
]
},
"_meta": {
"title": "Preview Mask"
}
},
"134": {
"class_type": "GetVideoComponents",
"inputs": {
"video": [
"197",
0
]
},
"_meta": {
"title": "Get Video Components"
}
},
"162": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"134",
1
],
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"134",
2
],
"images": [
"196:161",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"163": {
"class_type": "SaveVideo",
"inputs": {
"codec": "auto",
"filename_prefix": "video/ComfyUI-final",
"format": "auto",
"format.codec": "auto",
"video": [
"162",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"194": {
"class_type": "MaskToImage",
"inputs": {
"mask": [
"117:75",
0
]
},
"_meta": {
"title": "Convert Mask to Image"
}
},
"195": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"1",
0
],
"images.image1": [
"194",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"197": {
"class_type": "ByteDance2ReferenceNode",
"inputs": {
"model": "Seedance 2.0",
"model.auto_downscale": False,
"model.auto_upscale": False,
"model.duration": 7,
"model.generate_audio": True,
"model.prompt": [
"2",
0
],
"model.ratio": "adaptive",
"model.reference_images.image_1": [
"9",
0
],
"model.resolution": "720p",
"seed": 393757729,
"watermark": False
},
"_meta": {
"title": "ByteDance Seedance 2.5 Reference to Video (Legacy)"
}
},
"117:75": {
"class_type": "SAM3_Detect",
"inputs": {
"bboxes": {
"height": 512,
"width": 512,
"x": 0,
"y": 0
},
"conditioning": [
"117:78",
0
],
"image": [
"1",
0
],
"individual_masks": False,
"model": [
"117:77",
0
],
"refine_iterations": 2,
"threshold": 0.5
},
"_meta": {
"title": "SAM3 Detect"
}
},
"117:77": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "sam3.1_multiplex_fp16.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"117:78": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"117:77",
1
],
"text": "warrior, man, shield, sword"
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"196:141": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"196:142",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"196:142": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": 0,
"image": [
"134",
0
],
"length": 1
},
"_meta": {
"title": "Get Image from Batch"
}
},
"196:143": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 2,
"height": [
"196:141",
1
],
"image": [
"1",
0
],
"keep_proportion": "stretch",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": [
"196:141",
0
]
},
"_meta": {
"title": "Resize Image v2"
}
},
"196:151": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 2,
"height": [
"196:141",
1
],
"image": [
"196:155",
0
],
"keep_proportion": "stretch",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": [
"196:141",
0
]
},
"_meta": {
"title": "Resize Image v2"
}
},
"196:155": {
"class_type": "MaskToImage",
"inputs": {
"mask": [
"117:75",
0
]
},
"_meta": {
"title": "Convert Mask to Image"
}
},
"196:156": {
"class_type": "Image To Mask",
"inputs": {
"image": [
"196:151",
0
],
"method": "intensity"
},
"_meta": {
"title": "Image To Mask"
}
},
"196:158": {
"class_type": "GrowMaskWithBlur",
"inputs": {
"blur_radius": 0.5,
"decay_factor": 1,
"expand": 0,
"fill_holes": False,
"flip_input": False,
"incremental_expandrate": 0,
"lerp_alpha": 1,
"mask": [
"196:156",
0
],
"tapered_corners": True
},
"_meta": {
"title": "Grow Mask With Blur"
}
},
"196:161": {
"class_type": "ImageCompositeMasked",
"inputs": {
"destination": [
"134",
0
],
"mask": [
"196:158",
0
],
"resize_source": False,
"source": [
"196:143",
0
],
"x": 0,
"y": 0
},
"_meta": {
"title": "Image Composite Masked"
}
}
})
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)Perguntas e respostas
Use a etapa de máscara. Visualize a região animada com MaskPreview e refine a máscara antes de convertê-la com MaskToImage. Mantenha as bordas suaves para transições limpas e evite que a região de movimento cruze áreas de alto contraste, a menos que seja intencional.
Reduza a intensidade do movimento no ByteDance2ReferenceNode, diminua um pouco a duração e suavize as bordas da máscara. Também ajuste fps/duração em GetVideoComponents/CreateVideo para alinhar melhor os quadros inicial e final. Movimentos sutis geram loops mais suaves.
Retratos ou fotos de produto de alta qualidade e bem iluminados, com fundo relativamente limpo, produzem os melhores cinemagraphs. Formatos quadrados e verticais são ideais para redes sociais; defina o tamanho/fps de saída em GetVideoComponents/CreateVideo conforme sua plataforma alvo.
Não. Os nós f4cfd806-6db2-425e-9f50-3eb8fe546a77 e e42b05e2-13fc-4ad5-822d-b89a8a297d35 já estão pré-configurados para este fluxo. Deixe-os como estão, a menos que saiba o papel específico deles na sua instalação local.
Workflows relacionados
- Nano Banana Pro, Gemini3 Pro Image Preview, Google
Create a character turnaround
- Qwen-Image-Edit
Change a material
- Qwen-Image-Edit
See your subject from a new angle
- Flux.2 Dev, Flux
Create a product mockup
- Nano Banana Pro
Try an outfit on a character
- Seedream
Put your product in a new scene
- SSeedVR2
Upscale and restore detail
- Nano Banana Pro
Sharpen a product photo
- Topaz
Upscale an illustration
- HHitPaw
Restore portrait detail
- FLUX.1 Fill
Edit a selected region
- FLUX.1 Fill
Extend an image’s borders