DemonGatanjieuandClaude Opus 5.5
d0190a1eec
restyle reads a handed picture's outlines with ComfyUI's own Canny, holds the layout with the union ControlNet (canny mode, 0.7 to 80% of the steps) and redraws the whole picture in the prompt's new style. Tried on an RTX 4050 6 GB with SDXL (Illustrious) 832x1216: at denoise 0.8 it only got lighter, at 1.0 it became a watercolour with the layout held, so 1.0 is the default; about 41 s. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
120 lines
3.4 KiB
JSON
120 lines
3.4 KiB
JSON
{
|
||
"job": "follow",
|
||
"rank": 5,
|
||
"short": "new style",
|
||
"title": {
|
||
"zh": "换画风·构图不变",
|
||
"en": "New style, same layout"
|
||
},
|
||
"about": {
|
||
"zh": "你递给 AI 一张图，AMB 读出它的轮廓线（ComfyUI 自带的 Canny），用控制网把构图钉住，再按新画风整张重画（强度 1.0，原图的颜色只当参考）：人物、姿势、位置不变，画法换掉。AI 在提示词里写新画风。SDXL/NoobAI/Illustrious 用 Union 控制网。",
|
||
"en": "From a picture you hand the AI, its outlines (ComfyUI's own Canny) hold the layout through a ControlNet while the picture is redrawn whole in a new style (1.0, the old colours a hint only): who, pose and place stay, the way it is drawn changes. The prompt says the new style. SDXL, NoobAI and Illustrious use the union ControlNet."
|
||
},
|
||
"source": {
|
||
"zh": "常见的“控制网 + 以图生图”换风格做法，轮廓用 Union 控制网的 canny 模式",
|
||
"en": "The common ControlNet-plus-img2img restyle, the outlines through the union ControlNet's canny mode"
|
||
},
|
||
"packs": {},
|
||
"takes": "reference",
|
||
"control": "lineart",
|
||
"nodes": {
|
||
"reference": {
|
||
"class_type": "LoadImage",
|
||
"inputs": {
|
||
"image": "$image"
|
||
}
|
||
},
|
||
"edges": {
|
||
"class_type": "Canny",
|
||
"inputs": {
|
||
"image": [
|
||
"reference",
|
||
0
|
||
],
|
||
"low_threshold": 0.4,
|
||
"high_threshold": 0.8
|
||
}
|
||
},
|
||
"controlnet": {
|
||
"class_type": "ControlNetLoader",
|
||
"inputs": {
|
||
"control_net_name": "$controlnet"
|
||
}
|
||
},
|
||
"steer": {
|
||
"class_type": "ControlNetApplyAdvanced",
|
||
"inputs": {
|
||
"positive": [
|
||
"$sampler.positive",
|
||
"*"
|
||
],
|
||
"negative": [
|
||
"$sampler.negative",
|
||
"*"
|
||
],
|
||
"control_net": [
|
||
"controlnet",
|
||
0
|
||
],
|
||
"image": [
|
||
"edges",
|
||
0
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
],
|
||
"strength": 0.7,
|
||
"start_percent": 0.0,
|
||
"end_percent": 0.8
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"encode": {
|
||
"class_type": "VAEEncode",
|
||
"inputs": {
|
||
"pixels": [
|
||
"reference",
|
||
0
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
]
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"look": {
|
||
"class_type": "PreviewImage",
|
||
"inputs": {
|
||
"images": [
|
||
"edges",
|
||
0
|
||
]
|
||
}
|
||
}
|
||
},
|
||
"roles": {
|
||
"sampler": {
|
||
"denoise": 1.0
|
||
}
|
||
},
|
||
"after": "Write what is in the picture and the new style in the prompt (e.g. watercolor, flat colors, oil painting), or add_lora a style LoRA, then run_workflow. The size is the picture's. Its outlines are among the previews. To keep more of the old colours: lower the denoise to 0.8 (the style then changes less); the layout drifts: raise the ControlNet strength (0.7).",
|
||
"notes": "Canny outlines through the union ControlNet (its canny/lineart mode); Tried: denoise 0.8 kept the old look (only lighter); 1.0 gave the style, the outlines held the layout.",
|
||
"models": [
|
||
"union_promax_sdxl"
|
||
],
|
||
"tested": {
|
||
"gpu": "RTX 4050 Laptop",
|
||
"vram_gb": 6,
|
||
"date": "2026-10-28",
|
||
"runs": [
|
||
{
|
||
"model": "SDXL (Illustrious)",
|
||
"size": "832×1216",
|
||
"seconds": 41
|
||
}
|
||
]
|
||
}
|
||
}
|