Outpainting Vidéo
Outpainting vidéo avec le LTX 2.3 Video Outpainting IC LoRA. Étendez votre vidéo dans toutes les directions !
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 previewFichiers de ce workflow
- Sortie
- Vidéo
- Auteur
- Purz
Appelez 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({
"5060": {
"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": "Load Video (Upload) 🎥🅥🅗🅢"
}
},
"5069": {
"class_type": "VHS_VideoCombine",
"inputs": {
"audio": [
"5060",
2
],
"crf": 13,
"filename_prefix": "outpaint_comparison",
"format": "video/h264-mp4",
"frame_rate": [
"5151:5137",
5
],
"images": [
"5151:5125",
0
],
"loop_count": 0,
"pingpong": False,
"pix_fmt": "yuv420p",
"save_metadata": True,
"save_output": True,
"trim_to_audio": False
},
"_meta": {
"title": "video_compare"
}
},
"5152": {
"class_type": "VHS_VideoCombine",
"inputs": {
"audio": [
"5060",
2
],
"crf": 13,
"filename_prefix": "outpaint_output",
"format": "video/h264-mp4",
"frame_rate": [
"5151:5137",
5
],
"images": [
"5151:5143",
0
],
"loop_count": 0,
"pingpong": False,
"pix_fmt": "yuv420p",
"save_metadata": True,
"save_output": True,
"trim_to_audio": False
},
"_meta": {
"title": "video_output"
}
},
"5151:5097": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 16
},
"_meta": {
"title": "target_aspect_w"
}
},
"5151:5098": {
"class_type": "PrimitiveInt",
"inputs": {
"value": 9
},
"_meta": {
"title": "target_aspect_h"
}
},
"5151:5110": {
"class_type": "LTXVConditioning",
"inputs": {
"frame_rate": [
"5151:5137",
5
],
"negative": [
"5151:5131",
0
],
"positive": [
"5151:5138",
0
]
},
"_meta": {
"title": "LTXVConditioning"
}
},
"5151:5111": {
"class_type": "LTXVConcatAVLatent",
"inputs": {
"audio_latent": [
"5151:5121",
0
],
"video_latent": [
"5151:5142",
2
]
},
"_meta": {
"title": "Concat AV Latent"
}
},
"5151:5112": {
"class_type": "EmptyLTXVLatentVideo",
"inputs": {
"batch_size": 1,
"height": [
"5151:5126",
1
],
"length": [
"5151:5126",
2
],
"width": [
"5151:5126",
0
]
},
"_meta": {
"title": "Empty LTXV Latent Video"
}
},
"5151:5113": {
"class_type": "LTXVCropGuides",
"inputs": {
"latent": [
"5151:5114",
0
],
"negative": [
"5151:5142",
1
],
"positive": [
"5151:5142",
0
]
},
"_meta": {
"title": "LTXVCropGuides"
}
},
"5151:5114": {
"class_type": "LTXVSeparateAVLatent",
"inputs": {
"av_latent": [
"5151:5122",
0
]
},
"_meta": {
"title": "Separate AV Latent"
}
},
"5151:5115": {
"class_type": "CM_FloatToInt",
"inputs": {
"a": [
"5151:5137",
5
]
},
"_meta": {
"title": "FloatToInt"
}
},
"5151:5116": {
"class_type": "CFGGuider",
"inputs": {
"cfg": 1,
"model": [
"5151:5146",
0
],
"negative": [
"5151:5142",
1
],
"positive": [
"5151:5142",
0
]
},
"_meta": {
"title": "CFG Guider"
}
},
"5151:5117": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 617176731516609
},
"_meta": {
"title": "RandomNoise"
}
},
"5151:5118": {
"class_type": "ManualSigmas",
"inputs": {
"sigmas": "1.0, 0.99375, 0.9875, 0.98125, 0.975, 0.909375, 0.725, 0.421875, 0.0"
},
"_meta": {
"title": "ManualSigmas"
}
},
"5151:5119": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler_ancestral"
},
"_meta": {
"title": "KSamplerSelect"
}
},
"5151:5120": {
"class_type": "LTXVPreprocess",
"inputs": {
"image": [
"5151:5136",
0
],
"img_compression": 18
},
"_meta": {
"title": "LTXV Preprocess"
}
},
"5151:5121": {
"class_type": "LTXVEmptyLatentAudio",
"inputs": {
"audio_vae": [
"5151:5132",
0
],
"batch_size": 1,
"frame_rate": [
"5151:5115",
0
],
"frames_number": [
"5060",
1
]
},
"_meta": {
"title": "Empty LTXV Latent Audio"
}
},
"5151:5122": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"5151:5116",
0
],
"latent_image": [
"5151:5111",
0
],
"noise": [
"5151:5117",
0
],
"sampler": [
"5151:5119",
0
],
"sigmas": [
"5151:5118",
0
]
},
"_meta": {
"title": "SamplerCustomAdvanced"
}
},
"5151:5124": {
"class_type": "LTXVAudioVAEDecode",
"inputs": {
"audio_vae": [
"5151:5132",
0
],
"samples": [
"5151:5114",
1
]
},
"_meta": {
"title": "LTXV Audio VAE Decode"
}
},
"5151:5125": {
"class_type": "ImageConcanate",
"inputs": {
"direction": "left",
"image1": [
"5151:5143",
0
],
"image2": [
"5151:5130",
0
],
"match_image_size": True
},
"_meta": {
"title": "ImageConcanate"
}
},
"5151:5126": {
"class_type": "GetImageSize",
"inputs": {
"image": [
"5151:5130",
0
]
},
"_meta": {
"title": "Get Image Size"
}
},
"5151:5127": {
"class_type": "PrimitiveBoolean",
"inputs": {
"value": True
},
"_meta": {
"title": "bypass_i2v"
}
},
"5151:5128": {
"class_type": "VAEDecodeTiled",
"inputs": {
"overlap": 64,
"temporal_overlap": 4,
"temporal_size": 512,
"tile_size": 512
},
"_meta": {
"title": "VAE Decode (Tiled)"
}
},
"5151:5129": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"5151:5139",
0
],
"resize_type": "scale by multiplier",
"resize_type.multiplier": 0.5,
"scale_method": "lanczos"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"5151:5130": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"5151:5129",
0
],
"resize_type": "scale to multiple",
"resize_type.multiple": 32,
"scale_method": "area"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"5151:5131": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"5151:5135",
0
],
"text": "pc game, console game, video game, ugly, 3d render, photo, still, static, slow"
},
"_meta": {
"title": "CLIP Text Encode (Negative Prompt)"
}
},
"5151:5132": {
"class_type": "LTXVAudioVAELoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load LTXV Audio VAE"
}
},
"5151:5133": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors"
},
"_meta": {
"title": "Load Checkpoint"
}
},
"5151:5134": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2.3-22b-distilled-lora-384.safetensors",
"model": [
"5151:5133",
0
],
"strength_model": 0.5
},
"_meta": {
"title": "Load LoRA"
}
},
"5151:5135": {
"class_type": "LTXAVTextEncoderLoader",
"inputs": {
"ckpt_name": "ltx-2.3-22b-dev-fp8.safetensors",
"device": "default",
"text_encoder": "gemma_3_12B_it.safetensors"
},
"_meta": {
"title": "Load LTXV Audio Text Encoder"
}
},
"5151:5136": {
"class_type": "ResizeImageMaskNode",
"inputs": {
"input": [
"5151:5145",
0
],
"resize_type": "match size",
"resize_type.crop": "center",
"resize_type.match": [
"5151:5130",
0
],
"scale_method": "area"
},
"_meta": {
"title": "Resize Image/Mask"
}
},
"5151:5137": {
"class_type": "VHS_VideoInfo",
"inputs": {
"video_info": [
"5060",
3
]
},
"_meta": {
"title": "Video Info 🎥🅥🅗🅢"
}
},
"5151:5138": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": [
"5151:5135",
0
],
"text": "A wide, sunlit coastal desert opens out on both sides of the traveler: the shallow turquoise tidal channels keep winding left and right across the cracked salt flat, low sandstone bluffs run along the far horizon, and wind-carved dunes rise at the edges of the frame. The traveler in the billowing saffron and rust mantle stays braced on the sandbar in the middle while the gale streams golden sand across the whole scene. Harsh high-noon sun, glittering water, heat shimmer on the distant cliffs, consistent light and colour from edge to edge. Live-action footage with natural motion, the same steady slow push-in as the original clip, with seamless continuation of the water, sand and sky."
},
"_meta": {
"title": "CLIP Text Encode (Positive Prompt)"
}
},
"5151:5139": {
"class_type": "ImagePadKJ",
"inputs": {
"bottom": 0,
"color": "0, 0, 0",
"extra_padding": 0,
"image": [
"5060",
0
],
"left": 0,
"pad_mode": "color",
"right": 0,
"target_height": [
"5151:5150",
1
],
"target_width": [
"5151:5149",
1
],
"top": 0
},
"_meta": {
"title": "ImagePad KJ"
}
},
"5151:5140": {
"class_type": "VHS_VideoCombine",
"inputs": {
"audio": [
"5060",
2
],
"crf": 12,
"filename_prefix": "AnimateDiff",
"format": "video/h264-mp4",
"frame_rate": [
"5151:5137",
5
],
"images": [
"5151:5144",
0
],
"loop_count": 0,
"pingpong": False,
"pix_fmt": "yuv420p",
"save_metadata": True,
"save_output": False,
"trim_to_audio": False
},
"_meta": {
"title": "Video Combine 🎥🅥🅗🅢"
}
},
"5151:5141": {
"class_type": "LTXVImgToVideoConditionOnly",
"inputs": {
"bypass": [
"5151:5127",
0
],
"image": [
"5151:5120",
0
],
"latent": [
"5151:5112",
0
],
"strength": 0.7,
"vae": [
"5151:5133",
2
]
},
"_meta": {
"title": "🅛🅣🅧 LTXV Img To Video Condition Only"
}
},
"5151:5142": {
"class_type": "LTXAddVideoICLoRAGuide",
"inputs": {
"crop": "disabled",
"frame_idx": 0,
"image": [
"5151:5144",
0
],
"latent": [
"5151:5141",
0
],
"latent_downscale_factor": 1,
"negative": [
"5151:5110",
1
],
"positive": [
"5151:5110",
0
],
"strength": 1,
"tile_frames": 97,
"tile_overlap": 64,
"tile_size": 256,
"use_streaming": False,
"use_tiled_encode": False,
"vae": [
"5151:5133",
2
]
},
"_meta": {
"title": "🅛🅣🅧 Add Video IC-LoRA Guide"
}
},
"5151:5143": {
"class_type": "Float32ColorCorrect",
"inputs": {
"brightness": 0,
"clamp_output": False,
"contrast": 1,
"exposure": 0,
"gain_b": 1,
"gain_g": 1,
"gain_r": 1,
"gamma": 0.5,
"image": [
"5151:5154",
0
],
"lift_b": 0,
"lift_g": 0,
"lift_r": 0,
"luma_space": "Rec.709 / sRGB",
"saturation": 1
},
"_meta": {
"title": "◎ Radiance Float32 Color Correct"
}
},
"5151:5144": {
"class_type": "Float32ColorCorrect",
"inputs": {
"brightness": 0,
"clamp_output": False,
"contrast": 1,
"exposure": 0,
"gain_b": 1,
"gain_g": 1,
"gain_r": 1,
"gamma": 2,
"image": [
"5151:5130",
0
],
"lift_b": 0,
"lift_g": 0,
"lift_r": 0,
"luma_space": "Rec.709 / sRGB",
"saturation": 1
},
"_meta": {
"title": "◎ Radiance Float32 Color Correct"
}
},
"5151:5145": {
"class_type": "LoadImage",
"inputs": {
"image": "642ef66b933861a25a7a8ad3b46f3a7005c783d53c3971392a84595ae4dd4b04.png"
},
"_meta": {
"title": "Load Image"
}
},
"5151:5146": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "ltx-2.3-22b-ic-lora-outpaint.safetensors",
"model": [
"5151:5134",
0
],
"strength_model": 1
},
"_meta": {
"title": "Load LoRA"
}
},
"5151:5148": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "a / b",
"values.a": [
"5151:5097",
0
],
"values.b": [
"5151:5098",
0
]
},
"_meta": {
"title": "ratio"
}
},
"5151:5149": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "max(a, b * c)",
"values.a": [
"5151:5137",
3
],
"values.b": [
"5151:5137",
4
],
"values.c": [
"5151:5148",
0
]
},
"_meta": {
"title": "target_w"
}
},
"5151:5150": {
"class_type": "ComfyMathExpression",
"inputs": {
"expression": "max(b, a / c)",
"values.a": [
"5151:5137",
3
],
"values.b": [
"5151:5137",
4
],
"values.c": [
"5151:5148",
0
]
},
"_meta": {
"title": "target_h"
}
},
"5151:5154": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"5151:5113",
2
],
"vae": [
"5151:5133",
2
]
},
"_meta": {
"title": "VAE Decode"
}
}
})
workflow.set_input("5060", "video", client.assets.from_url("https://comfy.org/catalog-media/cb7672bb-ed5e-4001-a015-2d7a03cac864/5d2b5ac5-1ce8-4fbb-9922-52f2b9dc0da3"))
# 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("5152"):
output.to_file(output.name)
for output in job.get_outputs("5069"):
output.to_file(output.name)Essayer un exemple
À propos de ce workflow
Ce workflow ComfyUI effectue de l’outpainting vidéo : il étend la toile de chaque image de votre clip et synthétise du contenu crédible autour des images d’origine. Il charge votre vidéo source avec VHS_LoadVideo, traite les images avec un processeur d’outpainting personnalisé configuré pour utiliser le modèle LTX 2.3 Video Outpainting IC LoRA, puis réassemble les images en une vidéo finale avec VHS_VideoCombine. Une MarkdownNote dans le graphe fournit des indications directement dans le workflow.
Techniquement, l’étape centrale d’outpainting (ID de nœud personnalisé : 2e37ecc9-770a-4ac2-972c-e953901f49d3) ajoute du padding à l’image dans la/les direction(s) choisie(s), puis inpaint les zones nouvellement ajoutées tout en préservant le contenu original. Le modèle LTX 2.3 Video Outpainting IC LoRA conditionne le processus de diffusion afin que les bords générés restent cohérents stylistiquement et sémantiquement d’une image à l’autre. Le workflow expose deux contrôles clés de timeline : skip_first_frames (images à ignorer au début) et frame_count (nombre d’images à traiter après le skip). Par exemple, sur un clip de 600 images, vous pouvez définir skip_first_frames: 60 et frame_count: 480 pour traiter les images 60–539. Cela facilite les tests sur de courts segments avant de rendre toute la vidéo.
Comme il est basé sur des nœuds VHS, vous bénéficiez d’une extraction et d’une recombinaison fiables des images, ainsi que d’un contrôle simple de la cadence d’images et de l’emplacement de sortie. À utiliser quand vous devez convertir une vidéo verticale en format paysage, ajouter de la marge en haut/latérale pour recadrer, ou étendre un arrière-plan pour de nouveaux formats sans recadrage visible.
Questions-réponses
Non. VHS_VideoCombine produit une vidéo muette à partir des images traitées. Pour restaurer l’audio, remuxez-le depuis le clip original dans votre éditeur vidéo ou avec ffmpeg, ex : ffmpeg -i processed.mp4 -i source.mp4 -map 0:v -map 1:a -c copy out_with_audio.mp4.
skip_first_frames coupe le début, et frame_count limite le nombre d’images traitées après la coupe. Pour une vidéo de 600 images : skip_first_frames: 60 et frame_count: 480 traitent 480 images à partir de l’image 60. Utilisez des valeurs faibles pour tester rapidement avant de traiter tout le clip.
Utilisez un padding modéré, gardez la force/denoise raisonnable, et assurez-vous que le fps dans VHS_VideoCombine correspond à la source. Si le problème persiste, traitez la vidéo par segments courts avec des réglages adaptés, puis assemblez-les dans votre éditeur.
La VRAM dépend de la résolution, du padding et du batch size. Réduisez la résolution d’entrée, outpaintez une marge plus petite ou traitez moins d’images à la fois. Fermez les autres applications utilisant le GPU et vérifiez que les chemins LoRA/model sont corrects pour éviter les rechargements inutiles.