Wan2.2 Animate : Remplacement Automatique de Personnages
Téléchargez une vidéo et une image de personnage. Remplacez automatiquement le personnage dans la vidéo à l'aide du modèle Wan2.2 Animate.
Dans le workflow
Un aperçu en lecture seule du modèle source. Ouvrez-le dans Cloud pour explorer les nœuds et apporter des modifications.
Loading the graph
Open full-size workflow previewAppelez ce modèle depuis votre code
La requête ci-dessous utilise le même graphe préparé et les mêmes paramètres que le Playground. Chaque envoi peut lancer une exécution payante ; ne relancez pas automatiquement un envoi dont l’issue est inconnue.
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({
"10": {
"class_type": "LoadImage",
"inputs": {
"image": "UPLOADED_image_FILENAME"
},
"_meta": {
"title": "Reference Image"
}
},
"19": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"344:232:15",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"159": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 1280
},
"_meta": {
"title": "Width"
}
},
"160": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Height"
}
},
"301": {
"class_type": "VHS_LoadVideo",
"inputs": {
"custom_height": 0,
"custom_width": 0,
"force_rate": 0,
"format": "AnimateDiff",
"frame_load_cap": 0,
"select_every_nth": 1,
"skip_first_frames": 0,
"video": "UPLOADED_video_FILENAME"
},
"_meta": {
"title": "Input Video"
}
},
"314": {
"class_type": "VHS_VideoInfo",
"inputs": {
"video_info": [
"301",
3
]
},
"_meta": {
"title": "Video Info 🎥🅥🅗🅢"
}
},
"344:1": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"344:2",
0
],
"text": "色调艳丽,过曝,静态,细节模糊不清,字幕,风格,作品,画作,画面,静止,整体发灰,最差质量,低质量,JPEG压缩残留,丑陋的,残缺的,多余的手指,画得不好的手部,画得不好的脸部,畸形的,毁容的,形态畸形的肢体,手指融合,静止不动的画面,杂乱的背景,三条腿,背景人很多,倒着走"
},
"_meta": {
"title": "CLIP Text Encode (Negative Prompt)"
}
},
"344:18": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
"model": [
"344:20",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"344:2": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"device": "default",
"type": "wan"
},
"_meta": {
"title": "Load CLIP"
}
},
"344:20": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "Wan2_2-Animate-14B_fp8_e4m3fn_scaled_KJ.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model"
}
},
"344:21": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"344:2",
0
],
"text": "The post-apocalyptic elf warrior from the reference image dances alone in an empty night parking lot, taking over the dancer's exact moves. He bounces his shoulders, steps side to side in a relaxed groove, swings his arms low and wide, lifts a knee playfully and turns halfway on the spot before facing forward again. His tattered olive-green cloak flares and settles with each step, the alchemical vials on his belt sway and glint, and the cyan vents of the respirator around his neck glow softly. His blonde hair moves with the rhythm and his blue eyes stay on the camera. Warm amber streetlights light the cracked asphalt, parked white cars and autumn trees in the background, while distant red taillights glow through the dark. Smooth natural motion, consistent character, cinematic night photography."
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"344:232:15": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"314",
0
],
"images": [
"344:232:230",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"344:232:230": {
"class_type": "ImageFromBatch",
"inputs": {
"batch_index": [
"344:232:62",
4
],
"image": [
"344:232:58",
0
],
"length": 4096
},
"_meta": {
"title": "Get Image from Batch"
}
},
"344:232:57": {
"class_type": "TrimVideoLatent",
"inputs": {
"samples": [
"344:232:63",
0
],
"trim_amount": [
"344:232:62",
3
]
},
"_meta": {
"title": "Trim Video Latent"
}
},
"344:232:58": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"344:232:57",
0
],
"vae": [
"344:3",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"344:232:62": {
"class_type": "WanAnimateToVideo",
"inputs": {
"background_video": [
"344:332",
0
],
"batch_size": 1,
"character_mask": [
"344:325",
0
],
"clip_vision_output": [
"344:9",
0
],
"continue_motion_max_frames": 5,
"face_video": [
"344:334",
1
],
"height": [
"160",
0
],
"length": [
"301",
1
],
"negative": [
"344:1",
0
],
"pose_video": [
"344:335",
0
],
"positive": [
"344:21",
0
],
"reference_image": [
"344:342",
0
],
"vae": [
"344:3",
0
],
"video_frame_offset": 0,
"width": [
"159",
0
]
},
"_meta": {
"title": "WanAnimateToVideo"
}
},
"344:232:63": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"344:232:62",
2
],
"model": [
"344:60",
0
],
"negative": [
"344:232:62",
1
],
"positive": [
"344:232:62",
0
],
"sampler_name": "euler",
"scheduler": "simple",
"seed": [
"344:279",
0
],
"steps": 6
},
"_meta": {
"title": "KSampler"
}
},
"344:279": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 281253459907758
},
"_meta": {
"title": "Seed"
}
},
"344:3": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "wan_2.1_vae.safetensors"
},
"_meta": {
"title": "Load VAE"
}
},
"344:324": {
"class_type": "DownloadAndLoadSAM2Model",
"inputs": {
"device": "cuda",
"model": "sam2.1_hiera_base_plus.safetensors",
"precision": "fp16",
"segmentor": "video"
},
"_meta": {
"title": "(Down)Load SAM2Model"
}
},
"344:325": {
"class_type": "BlockifyMask",
"inputs": {
"block_size": 32,
"device": "cpu",
"masks": [
"344:327",
0
]
},
"_meta": {
"title": "Blockify Mask"
}
},
"344:326": {
"class_type": "Sam2Segmentation",
"inputs": {
"bboxes": [
"344:334",
3
],
"image": [
"344:338",
0
],
"individual_objects": False,
"keep_model_loaded": False,
"sam2_model": [
"344:324",
0
]
},
"_meta": {
"title": "Sam2Segmentation"
}
},
"344:327": {
"class_type": "GrowMaskWithBlur",
"inputs": {
"blur_radius": 0,
"decay_factor": 1,
"expand": 10,
"fill_holes": False,
"flip_input": False,
"incremental_expandrate": 0,
"lerp_alpha": 1,
"mask": [
"344:326",
0
],
"tapered_corners": True
},
"_meta": {
"title": "Grow Mask With Blur"
}
},
"344:328": {
"class_type": "OnnxDetectionModelLoader",
"inputs": {
"onnx_device": "CUDAExecutionProvider",
"vitpose_model": "vitpose-l-wholebody.onnx",
"yolo_model": "yolov10m.onnx"
},
"_meta": {
"title": "ONNX Detection Model Loader"
}
},
"344:329": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"344:333",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"344:330": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"344:340",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"344:331": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "video/ComfyUI",
"format": "auto",
"format.codec": "auto",
"video": [
"344:339",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"344:332": {
"class_type": "DrawMaskOnImage",
"inputs": {
"color": "0, 0, 0",
"device": "cpu",
"image": [
"344:338",
0
],
"mask": [
"344:325",
0
]
},
"_meta": {
"title": "Draw Mask On Image"
}
},
"344:333": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"314",
0
],
"images": [
"344:334",
1
]
},
"_meta": {
"title": "Create Video"
}
},
"344:334": {
"class_type": "PoseAndFaceDetection",
"inputs": {
"face_padding": 0,
"height": [
"344:348",
1
],
"images": [
"344:338",
0
],
"model": [
"344:328",
0
],
"width": [
"344:348",
0
]
},
"_meta": {
"title": "Pose and Face Detection"
}
},
"344:335": {
"class_type": "DrawViTPose",
"inputs": {
"body_stick_width": -1,
"draw_head": True,
"hand_stick_width": -1,
"height": [
"344:348",
1
],
"pose_data": [
"344:334",
0
],
"retarget_padding": 16,
"width": [
"344:348",
0
]
},
"_meta": {
"title": "Draw ViT Pose"
}
},
"344:338": {
"class_type": "ImageScale",
"inputs": {
"crop": "center",
"height": [
"160",
0
],
"image": [
"301",
0
],
"upscale_method": "lanczos",
"width": [
"159",
0
]
},
"_meta": {
"title": "Resize Input Video"
}
},
"344:339": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"314",
0
],
"images": [
"344:332",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"344:340": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"314",
0
],
"images": [
"344:335",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"344:342": {
"class_type": "ImageScale",
"inputs": {
"crop": "center",
"height": [
"160",
0
],
"image": [
"10",
0
],
"upscale_method": "lanczos",
"width": [
"159",
0
]
},
"_meta": {
"title": "Resize Reference Image"
}
},
"344:348": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"344:338",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"344:4": {
"class_type": "CLIPVisionLoader",
"inputs": {
"clip_name": "clip_vision_h.safetensors"
},
"_meta": {
"title": "Load CLIP Vision"
}
},
"344:60": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"344:99",
0
],
"shift": 8
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"344:9": {
"class_type": "CLIPVisionEncode",
"inputs": {
"clip_vision": [
"344:4",
0
],
"crop": "none",
"image": [
"344:342",
0
]
},
"_meta": {
"title": "CLIP Vision Encode"
}
},
"344:99": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "WanAnimate_relight_lora_fp16.safetensors",
"model": [
"344:18",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
}
})
workflow.set_input("10", "image", client.assets.from_url("https://comfy.org/catalog-media/c15207cf-eea0-4265-afa1-1f184889d1bb/8837ea56-961e-45d2-9f12-9a1e6671d461"))
workflow.set_input("301", "video", client.assets.from_url("https://comfy.org/catalog-media/75887865-03c0-4c13-ac9d-3ba726ac9737/d7153c54-caab-422e-8ed5-dd3349ee5243"))
# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)
for output in job.get_outputs("19"):
output.to_file(output.name)Essayer un exemple
À propos de ce workflow
Le workflow « Wan2.2 Animate : Remplacement Automatique de Personnage » est conçu pour remplacer de façon fluide un personnage dans une vidéo par un nouveau personnage issu d’une image téléchargée. Ceci est réalisé grâce au modèle Wan2.2 Animate, spécialisé dans l’animation et le remplacement de personnages. Le workflow commence par le chargement de votre vidéo et de l’image du personnage. Il traite ensuite ces entrées via une série de nœuds, dont ComfyUI-WanAnimatePreprocess pour la préparation initiale et ComfyUI-segment-anything-2 pour une segmentation précise. Cela garantit un remplacement de personnage précis et cohérent visuellement.
Techniquement, le workflow s’appuie sur une combinaison de nœuds vidéo comme VHS_LoadVideo et VHS_VideoInfo pour extraire et gérer les données vidéo. Le nœud b396d3e6-70cc-4a91-81db-6e0399a4edb6 est crucial pour les transformations complexes nécessaires à l’animation du personnage. En utilisant ces nœuds avec le modèle Wan2.2 Animate, vous obtenez des remplacements de personnages de haute qualité, stables et réalistes, surtout si l’image de référence montre clairement un sujet humain.
Questions-réponses
Des images de sujets humains avec un visage et des contours corporels nets produisent les résultats les plus stables et convaincants.
Le workflow est optimisé pour les humains, mais il peut fonctionner avec des personnages non humains, bien que les résultats puissent varier.
Le workflow prend en charge les formats vidéo standards, mais assurez-vous que votre vidéo est compatible avec le nœud VHS_LoadVideo.
Le temps de traitement dépend de la longueur et de la complexité de la vidéo, mais il faut généralement quelques minutes pour des clips courts.
Workflows associés
- wan2.2 Animate
3.2 Avancé : Contrôle de la génération vidéo
- wan2.2 Animate
Flux de travail de remplacement de personnage Wan Animate 2.2
- wan2.2 Animate
Vidéo d'Effet d'Expansion de Personnage Lora d'Inflation
- Wan, wan2.2 Animate
Wan2.2 Animate animation et remplacement de personnages
- SSCAIL-2
Replace a character in a video
- NNœud partenaire
SCAIL-2 : Remplacement de Personnage
- NNœud partenaire
Workflow d'Échange de Visage
- NNœud partenaire
Échange de visage
- NNœud partenaire
Échange de visage vidéo