DemonGatanjieuandClaude Opus 5.5
d95b2b309f
change_scene cuts the character out of a handed picture (inspyrenet-rembg), inverts it and redraws only the rest at denoise 1.0 from the prompt's new scene; GrowMask lets 6 px of the edge be redrawn for the seam. Tried on an RTX 4050 6 GB with SDXL (Illustrious) 832x1216: about 30 s, the character kept, the forest replaced by a night street. A picture handed to a block may be written "name.png [output]" as Load Image shows it. Two block descriptions are shorter so begin_task stays under 4000 characters. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
126 lines
3.3 KiB
JSON
126 lines
3.3 KiB
JSON
{
|
||
"job": "repaint",
|
||
"rank": 4,
|
||
"short": "new background",
|
||
"title": {
|
||
"zh": "换场景·人物不变",
|
||
"en": "New scene, same character"
|
||
},
|
||
"about": {
|
||
"zh": "你递给 AI 一张图，AMB 自动抠出人物，只重画人物以外的地方：AI 在提示词里写新场景，人物原样留下。人物边缘留几像素一起重画，让新背景和人物接得上。",
|
||
"en": "From a picture you hand the AI, the character is cut out automatically and everything else is drawn anew: the prompt says the new scene, the character stays as it was. A few pixels of its edge are redrawn too, so it sits in the new scene."
|
||
},
|
||
"source": {
|
||
"zh": "常见的“抠图换背景”做法：inspyrenet-rembg 抠人物，反选成背景，用 ComfyUI 自带的局部重绘节点只重画背景",
|
||
"en": "The common cut-out-and-replace-the-background way: inspyrenet-rembg finds the character, its inverse is the background, ComfyUI's own inpainting nodes redraw only that"
|
||
},
|
||
"packs": {
|
||
"InspyrenetRembg": "comfyui-inspyrenet-rembg"
|
||
},
|
||
"takes": "picture",
|
||
"nodes": {
|
||
"picture": {
|
||
"class_type": "LoadImage",
|
||
"inputs": {
|
||
"image": "$image"
|
||
}
|
||
},
|
||
"cut": {
|
||
"class_type": "InspyrenetRembg",
|
||
"inputs": {
|
||
"image": [
|
||
"picture",
|
||
0
|
||
],
|
||
"torchscript_jit": "default"
|
||
}
|
||
},
|
||
"background": {
|
||
"class_type": "InvertMask",
|
||
"inputs": {
|
||
"mask": [
|
||
"cut",
|
||
1
|
||
]
|
||
}
|
||
},
|
||
"edge": {
|
||
"class_type": "GrowMask",
|
||
"inputs": {
|
||
"mask": [
|
||
"background",
|
||
0
|
||
],
|
||
"expand": 6,
|
||
"tapered_corners": true
|
||
}
|
||
},
|
||
"soft": {
|
||
"class_type": "DifferentialDiffusion",
|
||
"inputs": {
|
||
"model": [
|
||
"$sampler.model",
|
||
"*"
|
||
]
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"encode": {
|
||
"class_type": "VAEEncode",
|
||
"inputs": {
|
||
"pixels": [
|
||
"picture",
|
||
0
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
]
|
||
}
|
||
},
|
||
"area": {
|
||
"class_type": "SetLatentNoiseMask",
|
||
"inputs": {
|
||
"samples": [
|
||
"encode",
|
||
0
|
||
],
|
||
"mask": [
|
||
"edge",
|
||
0
|
||
]
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"look": {
|
||
"class_type": "PreviewImage",
|
||
"inputs": {
|
||
"images": [
|
||
"cut",
|
||
0
|
||
]
|
||
}
|
||
}
|
||
},
|
||
"roles": {
|
||
"sampler": {
|
||
"denoise": 1.0
|
||
}
|
||
},
|
||
"after": "Write the new scene in the prompt and keep the character's own words (who, hair, clothes) so its edge fits, then run_workflow. The picture's size is the drawing's: the empty latent is no longer used. The kept character (cut out) is among the run's previews: if part of it is missing or the old background clings to it, say so; a halo at its edge: raise the GrowMask expand (6) a little.",
|
||
"notes": "Denoise 1.0: the background is drawn anew, not changed. GrowMask lets the background reach 6 px into the character so the seam is redrawn.",
|
||
"models": [],
|
||
"tested": {
|
||
"gpu": "RTX 4050 Laptop",
|
||
"vram_gb": 6,
|
||
"date": "2026-10-28",
|
||
"runs": [
|
||
{
|
||
"model": "SDXL (Illustrious)",
|
||
"size": "832×1216",
|
||
"seconds": 30
|
||
}
|
||
]
|
||
}
|
||
}
|