Files
DemonGatanjieu-Anomalous_Mo…/api/blocks/inpaint_basic.json
T
DemonGatanjieuandClaude Opus 5.5 88eaa77472 Make fixing one spot keep its size, and let picks zoom on it
Codex's hand tests (2026-10-29): at denoise 0.55-0.75 the repainted hand
filled its whole mark and came out too big, at 0.4 it kept its size. The
crop-and-stitch block now repaints at 0.45 (the built-in one at 0.5), and
its next step and the inpaint note tell the AI to mark tightly, keep the
strength low, make 4 tries and let the user pick.

Slider and picks blocks take a zoom {x, y, w, h}: every picture shows
only that part, enlarged, from the picture itself. The checks of block
parts move to ai_panel_parts.py (ai_panels.py was at the 600-line line).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-29 14:39:10 +08:00

73 lines
1.8 KiB
JSON

{
"job": "repaint",
"rank": 3,
"short": "built-in nodes",
"title": {
"zh": "局部重绘·官方节点",
"en": "Repaint: built-in nodes"
},
"about": {
"zh": "只用 ComfyUI 自带的节点重画圈出的地方,没装别的包时用。",
"en": "ComfyUI's own nodes only: for when the packs above are missing."
},
"source": {
"zh": "ComfyUI 官方的局部重绘做法",
"en": "ComfyUI's own way to inpaint"
},
"packs": {},
"takes": "inpaint",
"nodes": {
"picture": {
"class_type": "LoadImage",
"inputs": {
"image": "$image"
}
},
"soft": {
"class_type": "DifferentialDiffusion",
"inputs": {
"model": [
"$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": [
"picture",
1
]
},
"wire_to": "$sampler"
}
},
"roles": {
"sampler": {
"denoise": 0.5
}
},
"after": "The sampler repaints only the area, at denoise 0.5 so it keeps the picture's look (higher changes more). The marked area's size becomes the size of what is painted there: mark tightly around it (a hand, not the arm beside it). Keep denoise 0.35-0.5 to fix something and keep its size and pose; 0.7 and up paints a new thing that fills the whole mark. Hands and faces vary a lot from seed to seed: run_workflow with batch 4 and let the user pick, rather than judging one. Then run_workflow.",
"models": [],
"tested": {}
}