DemonGatanjieuandClaude Opus 5.5
5f336d39cd
The panel's text for each of the 18 blocks (about, zh and en) is one short sentence; where it came from and how it was tried stay under Details, the AI's instructions (after, notes) unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
182 lines
3.9 KiB
JSON
182 lines
3.9 KiB
JSON
{
|
||
"job": "new_background",
|
||
"want": "given",
|
||
"rank": 5,
|
||
"short": "given place",
|
||
"title": {
|
||
"zh": "放进另一张图",
|
||
"en": "Put a character into a picture"
|
||
},
|
||
"about": {
|
||
"zh": "把人物抠出来贴进你给的背景图，再轻轻重画让它融进去。",
|
||
"en": "Pastes the cut-out character into a given picture, then lightly redraws so it fits."
|
||
},
|
||
"source": {
|
||
"zh": "常见的“抠图合成再重绘融合”做法：inspyrenet-rembg 抠人物，ComfyUI 自带的节点缩放、贴图和局部重绘",
|
||
"en": "The common cut-out, composite and blend-by-redrawing way: inspyrenet-rembg finds the character, ComfyUI's own nodes scale, paste and redraw"
|
||
},
|
||
"packs": {
|
||
"InspyrenetRembg": "comfyui-inspyrenet-rembg"
|
||
},
|
||
"takes": "picture",
|
||
"scene": true,
|
||
"nodes": {
|
||
"picture": {
|
||
"class_type": "LoadImage",
|
||
"inputs": {
|
||
"image": "$image"
|
||
}
|
||
},
|
||
"place": {
|
||
"class_type": "LoadImage",
|
||
"inputs": {
|
||
"image": "$scene"
|
||
}
|
||
},
|
||
"cut": {
|
||
"class_type": "InspyrenetRembg",
|
||
"inputs": {
|
||
"image": [
|
||
"picture",
|
||
0
|
||
],
|
||
"torchscript_jit": "default"
|
||
}
|
||
},
|
||
"size": {
|
||
"class_type": "GetImageSize",
|
||
"inputs": {
|
||
"image": [
|
||
"picture",
|
||
0
|
||
]
|
||
}
|
||
},
|
||
"fit": {
|
||
"class_type": "ImageScale",
|
||
"inputs": {
|
||
"image": [
|
||
"place",
|
||
0
|
||
],
|
||
"upscale_method": "lanczos",
|
||
"width": [
|
||
"size",
|
||
0
|
||
],
|
||
"height": [
|
||
"size",
|
||
1
|
||
],
|
||
"crop": "center"
|
||
}
|
||
},
|
||
"paste": {
|
||
"class_type": "ImageCompositeMasked",
|
||
"inputs": {
|
||
"destination": [
|
||
"fit",
|
||
0
|
||
],
|
||
"source": [
|
||
"picture",
|
||
0
|
||
],
|
||
"x": 0,
|
||
"y": 0,
|
||
"resize_source": false,
|
||
"mask": [
|
||
"cut",
|
||
1
|
||
]
|
||
}
|
||
},
|
||
"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": [
|
||
"paste",
|
||
0
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
]
|
||
}
|
||
},
|
||
"area": {
|
||
"class_type": "SetLatentNoiseMask",
|
||
"inputs": {
|
||
"samples": [
|
||
"encode",
|
||
0
|
||
],
|
||
"mask": [
|
||
"edge",
|
||
0
|
||
]
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"look": {
|
||
"class_type": "PreviewImage",
|
||
"inputs": {
|
||
"images": [
|
||
"paste",
|
||
0
|
||
]
|
||
}
|
||
}
|
||
},
|
||
"roles": {
|
||
"sampler": {
|
||
"denoise": 0.5
|
||
}
|
||
},
|
||
"after": "Write both in the prompt, the character (who, hair, clothes) and the place as it looks, then run_workflow. The size is the character picture's; the place is cropped to it. The pasted picture before the redraw is among the previews. The place changes too much: lower the denoise (0.5); the character still looks pasted on: raise it a little.",
|
||
"notes": "Denoise 0.5 redraws the place lightly around the character, keeping its look; the character itself is not redrawn but for 6 px of its edge.",
|
||
"models": [],
|
||
"tested": {
|
||
"gpu": "RTX 4050 Laptop",
|
||
"vram_gb": 6,
|
||
"date": "2026-10-28",
|
||
"runs": [
|
||
{
|
||
"model": "SDXL (Illustrious)",
|
||
"size": "832×1216",
|
||
"seconds": 40
|
||
}
|
||
]
|
||
}
|
||
}
|