AIrt MAchIne
Téléversez n'importe quelle image pour générer une vidéo IA unique en boucle. Le flux de travail utilise un LLM pour créer cinq invites, produit des images et des clips vidéo, et les assemble en une boucle transparente finale.
À propos
Le flux de travail AIrt MAchIne dans ComfyUI est conçu pour transformer une image statique en une vidéo dynamique, en boucle, générée par IA. Le processus commence lorsque l’utilisateur téléverse une image, qui sert de base à la vidéo. Le flux de travail utilise un modèle de langage pour générer cinq prompts uniques à partir de l’image initiale, afin que chaque itération de la vidéo soit distincte et créative. Ces prompts guident la génération d’images et de courts clips vidéo, ensuite assemblés de façon continue pour former une boucle. Cela est réalisé via une série de nœuds, notamment ImageResizeKJv2 pour redimensionner les images, et VHS_VideoCombine pour fusionner les clips en une vidéo cohérente.
Sur le plan technique, le flux de travail s’appuie sur des modèles comme Wan2.2 et Z-Image-Turbo, connus pour leurs capacités efficaces de génération d’images et de vidéos. Des nœuds personnalisés tels que comfyui-kjnodes et comfyui-videohelpersuite sont utilisés pour améliorer les fonctionnalités du flux de travail, permettant un montage vidéo plus avancé et la génération de prompts. L’intégration de ces composants rend le flux de travail particulièrement utile aux artistes et aux créateurs de contenu qui souhaitent produire des vidéos uniques, pilotées par IA, à partir d’images statiques. De plus, les utilisateurs peuvent contourner certains nœuds, comme les groupes « Save frames » et « Save videos », s’ils souhaitent uniquement produire la vidéo finale combinée, ce qui offre de la flexibilité dans l’utilisation du flux de travail.
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 previewFichiers de ce workflow
- z_image_turbo_bf16.safetensors
- qwen_3_4b.safetensors
- ae.safetensors
- 4x-UltraSharp.safetensors
- umt5_xxl_fp8_e4m3fn_scaled.safetensors
- wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors
- wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors
- wan_2.1_vae.safetensors
- wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_1022.safetensors
- wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_1022.safetensors
- Auteur
- Julien Durand | MJM
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({
"5": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 1,
"height": [
"163",
0
],
"image": [
"99:77",
0
],
"keep_proportion": "crop",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": [
"162",
0
]
},
"_meta": {
"title": "Resize Image v2"
}
},
"9": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 1,
"height": [
"163",
0
],
"image": [
"103:241",
0
],
"keep_proportion": "crop",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": [
"162",
0
]
},
"_meta": {
"title": "Resize Image v2"
}
},
"10": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Clips/MJM_AIrtMAchIne_Vid1",
"format": "auto",
"format.codec": "auto",
"video": [
"204",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"14": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 1,
"height": [
"163",
0
],
"image": [
"107:252",
0
],
"keep_proportion": "crop",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": [
"162",
0
]
},
"_meta": {
"title": "Resize Image v2"
}
},
"16": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Clips/MJM_AIrtMAchIne_Vid2",
"format": "auto",
"format.codec": "auto",
"video": [
"220",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"20": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 1,
"height": [
"163",
0
],
"image": [
"111:267",
0
],
"keep_proportion": "crop",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": [
"162",
0
]
},
"_meta": {
"title": "Resize Image v2"
}
},
"22": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Clips/MJM_AIrtMAchIne_Vid3",
"format": "auto",
"format.codec": "auto",
"video": [
"222",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"25": {
"class_type": "ImageResizeKJv2",
"inputs": {
"crop_position": "center",
"device": "cpu",
"divisible_by": 1,
"height": [
"163",
0
],
"image": [
"115:277",
0
],
"keep_proportion": "crop",
"pad_color": "0, 0, 0",
"upscale_method": "lanczos",
"width": [
"162",
0
]
},
"_meta": {
"title": "Resize Image v2"
}
},
"27": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Clips/MJM_AIrtMAchIne_Vid4",
"format": "auto",
"format.codec": "auto",
"video": [
"226",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"33": {
"class_type": "SaveVideo",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Clips/MJM_AIrtMAchIne_Vid5",
"format": "auto",
"format.codec": "auto",
"video": [
"227",
0
]
},
"_meta": {
"title": "Save Video"
}
},
"94": {
"class_type": "LoadImage",
"inputs": {
"image": "AIrt_MAchIne_init.png"
},
"_meta": {
"title": "Load Image"
}
},
"100": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"99:73",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"104": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"103:240",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"108": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"107:255",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"112": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"111:264",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"116": {
"class_type": "PreviewImage",
"inputs": {
"images": [
"115:276",
0
]
},
"_meta": {
"title": "Preview Image"
}
},
"126": {
"class_type": "BatchImagesNode",
"inputs": {
"images.image0": [
"217:203",
0
],
"images.image1": [
"219:284",
0
],
"images.image2": [
"221:294",
0
],
"images.image3": [
"225:304",
0
],
"images.image4": [
"228:314",
0
]
},
"_meta": {
"title": "Batch Images"
}
},
"131": {
"class_type": "VHS_VideoCombine",
"inputs": {
"crf": 14,
"filename_prefix": "MJM/AIrt MAchIne/Final/MJM_AIrtMAchIne",
"format": "video/h264-mp4",
"frame_rate": [
"230",
0
],
"images": [
"126",
0
],
"loop_count": 0,
"pingpong": False,
"pix_fmt": "yuv420p",
"save_metadata": True,
"save_output": True,
"trim_to_audio": False
},
"_meta": {
"title": "Video Combine 🎥🅥🅗🅢"
}
},
"152": {
"class_type": "ImpactStringSelector",
"inputs": {
"multiline": False,
"select": 0,
"strings": [
"323",
0
]
},
"_meta": {
"title": "String Selector"
}
},
"153": {
"class_type": "ImpactStringSelector",
"inputs": {
"multiline": False,
"select": 1,
"strings": [
"323",
0
]
},
"_meta": {
"title": "String Selector"
}
},
"154": {
"class_type": "ImpactStringSelector",
"inputs": {
"multiline": False,
"select": 2,
"strings": [
"323",
0
]
},
"_meta": {
"title": "String Selector"
}
},
"155": {
"class_type": "ImpactStringSelector",
"inputs": {
"multiline": False,
"select": 3,
"strings": [
"323",
0
]
},
"_meta": {
"title": "String Selector"
}
},
"156": {
"class_type": "ImpactStringSelector",
"inputs": {
"multiline": False,
"select": 4,
"strings": [
"323",
0
]
},
"_meta": {
"title": "String Selector"
}
},
"161": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Frames/MJM_AIrtMAchIne_Im1",
"images": [
"5",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"162": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Width"
}
},
"163": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 720
},
"_meta": {
"title": "Height"
}
},
"164": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Frames/MJM_AIrtMAchIne_Im2",
"images": [
"9",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"165": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Frames/MJM_AIrtMAchIne_Im3",
"images": [
"14",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"166": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Frames/MJM_AIrtMAchIne_Im4",
"images": [
"20",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"167": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "MJM/AIrt MAchIne/Frames/MJM_AIrtMAchIne_Im5",
"images": [
"25",
0
]
},
"_meta": {
"title": "Save Image"
}
},
"168": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"323",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"169": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"152",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"171": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"153",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"172": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"154",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"173": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"155",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"174": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"156",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"175": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"217:324",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"177": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"219:325",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"178": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"221:326",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"179": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"225:327",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"180": {
"class_type": "PreviewAny",
"inputs": {
"source": [
"228:328",
0
]
},
"_meta": {
"title": "Preview as Text"
}
},
"186": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "z_image_turbo_bf16.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model - Z-Image Turbo"
}
},
"187": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen_3_4b.safetensors",
"device": "default",
"type": "lumina2"
},
"_meta": {
"title": "Load CLIP - Z-Image Turbo"
}
},
"188": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "ae.safetensors"
},
"_meta": {
"title": "Load VAE - Z-Image Turbo"
}
},
"194": {
"class_type": "UpscaleModelLoader",
"inputs": {
"model_name": "4x-UltraSharp.safetensors"
},
"_meta": {
"title": "Load Upscale Model - For Z-Image Turbo"
}
},
"195": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"device": "default",
"type": "wan"
},
"_meta": {
"title": "Load CLIP - Wan 2.2"
}
},
"198": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model - Wan 2.2"
}
},
"199": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors",
"weight_dtype": "default"
},
"_meta": {
"title": "Load Diffusion Model - Wan 2.2"
}
},
"201": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "wan_2.1_vae.safetensors"
},
"_meta": {
"title": "Load VAE - Wan 2.2"
}
},
"204": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"230",
0
],
"images": [
"217:203",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"220": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"230",
0
],
"images": [
"219:284",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"222": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"230",
0
],
"images": [
"221:294",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"226": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"230",
0
],
"images": [
"225:304",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"227": {
"class_type": "CreateVideo",
"inputs": {
"bit_depth": "auto",
"codec": "none",
"color_space": "sRGB",
"fps": [
"230",
0
],
"images": [
"228:314",
0
]
},
"_meta": {
"title": "Create Video"
}
},
"230": {
"class_type": "PrimitiveFloat",
"inputs": {
"value": 24
},
"_meta": {
"title": "FPS"
}
},
"231": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_1022.safetensors",
"model": [
"198",
0
],
"strength_model": 1.0000000000000002
},
"_meta": {
"title": "Load LoRA"
}
},
"232": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_1022.safetensors",
"model": [
"199",
0
],
"strength_model": 1.0000000000000002
},
"_meta": {
"title": "Load LoRA"
}
},
"323": {
"class_type": "AILab_QwenVL",
"inputs": {
"attention_mode": "auto",
"custom_prompt": "write 5 prompts based on this image, I will use these in a text 2 image model. The prompts should be different, be creative. Only use the image as inspiration.\n\nI want only the prompts and nothing else. Each prompt on its own line.\n\nNo empty lines in-between the prompts:\nPrompt 1\nPrompt 2\nPrompt 3\nPrompt 4\nPrompt 5",
"image": [
"94",
0
],
"keep_model_loaded": True,
"max_tokens": 1024,
"model_name": "Qwen3-VL-8B-Instruct",
"preset_prompt": "🖼️ Detailed Description",
"quantization": "None (FP16)",
"seed": 2922644121
},
"_meta": {
"title": "QwenVL"
}
},
"103:236": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"103:237",
0
],
"model": [
"103:238",
0
],
"negative": [
"103:246",
0
],
"positive": [
"103:244",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 459413941250020,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"103:237": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"batch_size": 1,
"height": [
"163",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "EmptySD3LatentImage"
}
},
"103:238": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"186",
0
],
"sampling": "flow",
"shift": 3
},
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"103:240": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"103:236",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"103:241": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"103:242",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"103:242": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 0.2,
"latent_image": [
"103:243",
0
],
"model": [
"103:238",
0
],
"negative": [
"103:246",
0
],
"positive": [
"103:244",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 974,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"103:243": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"103:98",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"103:244": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"187",
0
],
"text": [
"153",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"103:246": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"103:244",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"103:98": {
"class_type": "ImageUpscaleWithModelBatched",
"inputs": {
"downscale_method": "bicubic",
"downscale_ratio": 0.5,
"images": [
"103:240",
0
],
"per_batch": 1,
"precision": "bfloat16",
"upscale_model": [
"194",
0
]
},
"_meta": {
"title": "Image Upscale With Model Batched"
}
},
"107:247": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"107:248",
0
],
"model": [
"107:249",
0
],
"negative": [
"107:258",
0
],
"positive": [
"107:256",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 417454711451413,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"107:248": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"batch_size": 1,
"height": [
"163",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "EmptySD3LatentImage"
}
},
"107:249": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"186",
0
],
"sampling": "flow",
"shift": 3
},
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"107:251": {
"class_type": "ImageUpscaleWithModelBatched",
"inputs": {
"downscale_method": "bicubic",
"downscale_ratio": 0.5,
"images": [
"107:255",
0
],
"per_batch": 1,
"precision": "bfloat16",
"upscale_model": [
"194",
0
]
},
"_meta": {
"title": "Image Upscale With Model Batched"
}
},
"107:252": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"107:253",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"107:253": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 0.2,
"latent_image": [
"107:254",
0
],
"model": [
"107:249",
0
],
"negative": [
"107:258",
0
],
"positive": [
"107:256",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 974,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"107:254": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"107:251",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"107:255": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"107:247",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"107:256": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"187",
0
],
"text": [
"154",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"107:258": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"107:256",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"111:259": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"111:260",
0
],
"model": [
"111:261",
0
],
"negative": [
"111:270",
0
],
"positive": [
"111:269",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 392438948527137,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"111:260": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"batch_size": 1,
"height": [
"163",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "EmptySD3LatentImage"
}
},
"111:261": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"186",
0
],
"sampling": "flow",
"shift": 3
},
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"111:264": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"111:259",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"111:265": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"111:268",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"111:266": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 0.2,
"latent_image": [
"111:265",
0
],
"model": [
"111:261",
0
],
"negative": [
"111:270",
0
],
"positive": [
"111:269",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 974,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"111:267": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"111:266",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"111:268": {
"class_type": "ImageUpscaleWithModelBatched",
"inputs": {
"downscale_method": "bicubic",
"downscale_ratio": 0.5,
"images": [
"111:264",
0
],
"per_batch": 1,
"precision": "bfloat16",
"upscale_model": [
"194",
0
]
},
"_meta": {
"title": "Image Upscale With Model Batched"
}
},
"111:269": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"187",
0
],
"text": [
"155",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"111:270": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"111:269",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"115:271": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"115:272",
0
],
"model": [
"115:273",
0
],
"negative": [
"115:282",
0
],
"positive": [
"115:281",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 123941752424153,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"115:272": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"batch_size": 1,
"height": [
"163",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "EmptySD3LatentImage"
}
},
"115:273": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"186",
0
],
"sampling": "flow",
"shift": 3
},
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"115:276": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"115:271",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"115:277": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"115:278",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"115:278": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 0.2,
"latent_image": [
"115:279",
0
],
"model": [
"115:273",
0
],
"negative": [
"115:282",
0
],
"positive": [
"115:281",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 974,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"115:279": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"115:280",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Encode"
}
},
"115:280": {
"class_type": "ImageUpscaleWithModelBatched",
"inputs": {
"downscale_method": "bicubic",
"downscale_ratio": 0.5,
"images": [
"115:276",
0
],
"per_batch": 1,
"precision": "bfloat16",
"upscale_model": [
"194",
0
]
},
"_meta": {
"title": "Image Upscale With Model Batched"
}
},
"115:281": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"187",
0
],
"text": [
"156",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"115:282": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"115:281",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"217:196": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"231",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"217:197": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"232",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"217:200": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
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)"
}
},
"217:202": {
"class_type": "WanFirstLastFrameToVideo",
"inputs": {
"batch_size": 1,
"end_image": [
"9",
0
],
"height": [
"163",
0
],
"length": 81,
"negative": [
"217:200",
0
],
"positive": [
"217:206",
0
],
"start_image": [
"5",
0
],
"vae": [
"201",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "WanFirstLastFrameToVideo"
}
},
"217:203": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"217:212",
0
],
"vae": [
"201",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"217:206": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
0
],
"text": [
"217:324",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"217:211": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "enable",
"cfg": 1,
"end_at_step": 2,
"latent_image": [
"217:202",
2
],
"model": [
"217:196",
0
],
"negative": [
"217:202",
1
],
"noise_seed": 1036176414007226,
"positive": [
"217:202",
0
],
"return_with_leftover_noise": "enable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 0,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"217:212": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "disable",
"cfg": 1,
"end_at_step": 10000,
"latent_image": [
"217:211",
0
],
"model": [
"217:197",
0
],
"negative": [
"217:202",
1
],
"noise_seed": 0,
"positive": [
"217:202",
0
],
"return_with_leftover_noise": "disable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 2,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"217:215": {
"class_type": "ImageBatchMulti",
"inputs": {
"image_1": [
"5",
0
],
"image_2": [
"9",
0
],
"inputcount": 2
},
"_meta": {
"title": "Image Batch Multi"
}
},
"217:324": {
"class_type": "AILab_QwenVL",
"inputs": {
"attention_mode": "auto",
"custom_prompt": "Write a wild prompt for a video model that will take first and last frame. Maximize motion and go crazy. Give me the prompt and nothing else.",
"image": [
"217:215",
0
],
"keep_model_loaded": False,
"max_tokens": 1024,
"model_name": "Qwen3-VL-8B-Instruct",
"preset_prompt": "🖼️ Detailed Description",
"quantization": "None (FP16)",
"seed": 826063256
},
"_meta": {
"title": "QwenVL"
}
},
"219:283": {
"class_type": "WanFirstLastFrameToVideo",
"inputs": {
"batch_size": 1,
"end_image": [
"14",
0
],
"height": [
"163",
0
],
"length": 81,
"negative": [
"219:287",
0
],
"positive": [
"219:286",
0
],
"start_image": [
"9",
0
],
"vae": [
"201",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "WanFirstLastFrameToVideo"
}
},
"219:284": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"219:290",
0
],
"vae": [
"201",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"219:285": {
"class_type": "ImageBatchMulti",
"inputs": {
"image_1": [
"9",
0
],
"image_2": [
"14",
0
],
"inputcount": 2
},
"_meta": {
"title": "Image Batch Multi"
}
},
"219:286": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
0
],
"text": [
"219:325",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"219:287": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
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)"
}
},
"219:289": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "enable",
"cfg": 1,
"end_at_step": 2,
"latent_image": [
"219:283",
2
],
"model": [
"219:291",
0
],
"negative": [
"219:283",
1
],
"noise_seed": 1044595221991389,
"positive": [
"219:283",
0
],
"return_with_leftover_noise": "enable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 0,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"219:290": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "disable",
"cfg": 1,
"end_at_step": 10000,
"latent_image": [
"219:289",
0
],
"model": [
"219:292",
0
],
"negative": [
"219:283",
1
],
"noise_seed": 0,
"positive": [
"219:283",
0
],
"return_with_leftover_noise": "disable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 2,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"219:291": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"231",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"219:292": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"232",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"219:325": {
"class_type": "AILab_QwenVL",
"inputs": {
"attention_mode": "auto",
"custom_prompt": "Write a wild prompt for a video model that will take first and last frame. Maximize motion and go crazy. Give me the prompt and nothing else.",
"image": [
"219:285",
0
],
"keep_model_loaded": False,
"max_tokens": 1024,
"model_name": "Qwen3-VL-8B-Instruct",
"preset_prompt": "🖼️ Detailed Description",
"quantization": "None (FP16)",
"seed": 1738501745
},
"_meta": {
"title": "QwenVL"
}
},
"221:293": {
"class_type": "WanFirstLastFrameToVideo",
"inputs": {
"batch_size": 1,
"end_image": [
"20",
0
],
"height": [
"163",
0
],
"length": 81,
"negative": [
"221:297",
0
],
"positive": [
"221:296",
0
],
"start_image": [
"14",
0
],
"vae": [
"201",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "WanFirstLastFrameToVideo"
}
},
"221:294": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"221:299",
0
],
"vae": [
"201",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"221:295": {
"class_type": "ImageBatchMulti",
"inputs": {
"image_1": [
"14",
0
],
"image_2": [
"20",
0
],
"inputcount": 2
},
"_meta": {
"title": "Image Batch Multi"
}
},
"221:296": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
0
],
"text": [
"221:326",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"221:297": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
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)"
}
},
"221:299": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "disable",
"cfg": 1,
"end_at_step": 10000,
"latent_image": [
"221:300",
0
],
"model": [
"221:302",
0
],
"negative": [
"221:293",
1
],
"noise_seed": 0,
"positive": [
"221:293",
0
],
"return_with_leftover_noise": "disable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 2,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"221:300": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "enable",
"cfg": 1,
"end_at_step": 2,
"latent_image": [
"221:293",
2
],
"model": [
"221:301",
0
],
"negative": [
"221:293",
1
],
"noise_seed": 870123508735268,
"positive": [
"221:293",
0
],
"return_with_leftover_noise": "enable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 0,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"221:301": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"231",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"221:302": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"232",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"221:326": {
"class_type": "AILab_QwenVL",
"inputs": {
"attention_mode": "auto",
"custom_prompt": "Write a wild prompt for a video model that will take first and last frame. Maximize motion and go crazy. Give me the prompt and nothing else.",
"image": [
"221:295",
0
],
"keep_model_loaded": False,
"max_tokens": 1024,
"model_name": "Qwen3-VL-8B-Instruct",
"preset_prompt": "🖼️ Detailed Description",
"quantization": "None (FP16)",
"seed": 1736034325
},
"_meta": {
"title": "QwenVL"
}
},
"225:303": {
"class_type": "WanFirstLastFrameToVideo",
"inputs": {
"batch_size": 1,
"end_image": [
"25",
0
],
"height": [
"163",
0
],
"length": 81,
"negative": [
"225:307",
0
],
"positive": [
"225:306",
0
],
"start_image": [
"20",
0
],
"vae": [
"201",
0
],
"width": [
"163",
0
]
},
"_meta": {
"title": "WanFirstLastFrameToVideo"
}
},
"225:304": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"225:309",
0
],
"vae": [
"201",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"225:305": {
"class_type": "ImageBatchMulti",
"inputs": {
"image_1": [
"20",
0
],
"image_2": [
"25",
0
],
"inputcount": 2
},
"_meta": {
"title": "Image Batch Multi"
}
},
"225:306": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
0
],
"text": [
"225:327",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"225:307": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
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)"
}
},
"225:309": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "disable",
"cfg": 1,
"end_at_step": 10000,
"latent_image": [
"225:310",
0
],
"model": [
"225:311",
0
],
"negative": [
"225:303",
1
],
"noise_seed": 0,
"positive": [
"225:303",
0
],
"return_with_leftover_noise": "disable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 2,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"225:310": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "enable",
"cfg": 1,
"end_at_step": 2,
"latent_image": [
"225:303",
2
],
"model": [
"225:312",
0
],
"negative": [
"225:303",
1
],
"noise_seed": 649177653589995,
"positive": [
"225:303",
0
],
"return_with_leftover_noise": "enable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 0,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"225:311": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"232",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"225:312": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"231",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"225:327": {
"class_type": "AILab_QwenVL",
"inputs": {
"attention_mode": "auto",
"custom_prompt": "Write a wild prompt for a video model that will take first and last frame. Maximize motion and go crazy. Give me the prompt and nothing else.",
"image": [
"225:305",
0
],
"keep_model_loaded": False,
"max_tokens": 1024,
"model_name": "Qwen3-VL-8B-Instruct",
"preset_prompt": "🖼️ Detailed Description",
"quantization": "None (FP16)",
"seed": 479492193
},
"_meta": {
"title": "QwenVL"
}
},
"228:313": {
"class_type": "WanFirstLastFrameToVideo",
"inputs": {
"batch_size": 1,
"end_image": [
"5",
0
],
"height": [
"163",
0
],
"length": 81,
"negative": [
"228:317",
0
],
"positive": [
"228:316",
0
],
"start_image": [
"25",
0
],
"vae": [
"201",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "WanFirstLastFrameToVideo"
}
},
"228:314": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"228:320",
0
],
"vae": [
"201",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"228:315": {
"class_type": "ImageBatchMulti",
"inputs": {
"image_1": [
"25",
0
],
"image_2": [
"5",
0
],
"inputcount": 2
},
"_meta": {
"title": "Image Batch Multi"
}
},
"228:316": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
0
],
"text": [
"228:328",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"228:317": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"195",
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)"
}
},
"228:319": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "enable",
"cfg": 1,
"end_at_step": 2,
"latent_image": [
"228:313",
2
],
"model": [
"228:321",
0
],
"negative": [
"228:313",
1
],
"noise_seed": 75596193383703,
"positive": [
"228:313",
0
],
"return_with_leftover_noise": "enable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 0,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"228:320": {
"class_type": "KSamplerAdvanced",
"inputs": {
"add_noise": "disable",
"cfg": 1,
"end_at_step": 10000,
"latent_image": [
"228:319",
0
],
"model": [
"228:322",
0
],
"negative": [
"228:313",
1
],
"noise_seed": 0,
"positive": [
"228:313",
0
],
"return_with_leftover_noise": "disable",
"sampler_name": "euler",
"scheduler": "simple",
"start_at_step": 2,
"steps": 4
},
"_meta": {
"title": "KSampler (Advanced)"
}
},
"228:321": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"231",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"228:322": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": [
"232",
0
],
"shift": 5
},
"_meta": {
"title": "ModelSamplingSD3"
}
},
"228:328": {
"class_type": "AILab_QwenVL",
"inputs": {
"attention_mode": "auto",
"custom_prompt": "Write a wild prompt for a video model that will take first and last frame. Maximize motion and go crazy. Give me the prompt and nothing else.",
"image": [
"228:315",
0
],
"keep_model_loaded": False,
"max_tokens": 1024,
"model_name": "Qwen3-VL-8B-Instruct",
"preset_prompt": "🖼️ Detailed Description",
"quantization": "None (FP16)",
"seed": 1455269179
},
"_meta": {
"title": "QwenVL"
}
},
"99:234": {
"class_type": "ImageUpscaleWithModelBatched",
"inputs": {
"downscale_method": "bicubic",
"downscale_ratio": 0.5,
"images": [
"99:73",
0
],
"per_batch": 1,
"precision": "bfloat16",
"upscale_model": [
"194",
0
]
},
"_meta": {
"title": "Image Upscale With Model Batched"
}
},
"99:235": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 0.2,
"latent_image": [
"99:97",
0
],
"model": [
"99:69",
0
],
"negative": [
"99:70",
0
],
"positive": [
"99:72",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 974,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"99:66": {
"class_type": "KSampler",
"inputs": {
"cfg": 1,
"denoise": 1,
"latent_image": [
"99:79",
0
],
"model": [
"99:69",
0
],
"negative": [
"99:70",
0
],
"positive": [
"99:72",
0
],
"sampler_name": "res_multistep",
"scheduler": "simple",
"seed": 120051025389428,
"steps": 9
},
"_meta": {
"title": "KSampler"
}
},
"99:69": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": [
"186",
0
],
"sampling": "flow",
"shift": 3
},
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"99:70": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": [
"99:72",
0
]
},
"_meta": {
"title": "Conditioning Zero Out"
}
},
"99:72": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"187",
0
],
"text": [
"152",
0
]
},
"_meta": {
"title": "CLIP Text Encode (Prompt)"
}
},
"99:73": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"99:66",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"99:77": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"99:235",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Decode"
}
},
"99:79": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"batch_size": 1,
"height": [
"163",
0
],
"width": [
"162",
0
]
},
"_meta": {
"title": "EmptySD3LatentImage"
}
},
"99:97": {
"class_type": "VAEEncode",
"inputs": {
"pixels": [
"99:234",
0
],
"vae": [
"188",
0
]
},
"_meta": {
"title": "VAE Encode"
}
}
})
# 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 télécharger n'importe quelle image comme point de départ pour la génération vidéo.
Le workflow utilise les modèles Wan2.2 et Z-Image-Turbo pour la génération d'images et de vidéos.
Oui, vous pouvez choisir d'enregistrer les images individuelles en utilisant le groupe 'Save frames' dans le workflow.
Le workflow est conçu pour assembler automatiquement les clips vidéo en une boucle fluide grâce au nœud VHS_VideoCombine.
Workflows associés
- Qwen-Image-Edit, Wan2.2
1 entrée d'image Pile divisée - Qwen Multiangle + Wan 2.2
- Wan2.2
1.2 Démarrage – Image vers Vidéo
- Wan, Wan2.2
Image vers Vidéo (Nouveau)
- Wan2.2
Remplacement du ciel
- Nano Banana, Google Gemini, Wan2.2
Restyleur en Boucle
- Wan2.2
Vidéo reliée début-fin en continu
- Wan2.2, Wan
Wan 2.2 14B Contrôle Caméra Fun
- Wan2.2, Wan
Wan 2.2 14B Fun Control
- Wan2.2, Wan
Wan 2.2 14B Fun Inpainting
- Wan, Wan2.2
Wan 2.2 14B image vers vidéo
- Wan2.2, Wan
Wan 2.2 14B Première-Dernière frame en Vidéo
- Wan2.2, Wan
Wan 2.2 14B texte vers vidéo