DemonGatanjieuandClaude Opus 5.5
d0d9afc48c
The hand fix's "3 tries in 4" holds for the pictures tried, not for crowds or hard poses; its checks now compare with the enlarged redraw and look for seams, missed hands and good hands made worse. Enlarging at the mid-way switch asks the user first when the workflow already enlarges the picture downstream. Both ways record GPT's runs. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
490 lines
15 KiB
JSON
490 lines
15 KiB
JSON
{
|
||
"job": "detail",
|
||
"want": "hands",
|
||
"rank": 2,
|
||
"short": "enlarge, then hands (fallback)",
|
||
"enlarge": {
|
||
"megapixels": 4.2,
|
||
"most": 2.0,
|
||
"unknown": 1.5
|
||
},
|
||
"title": {
|
||
"zh": "修手·先放大再修（备选）",
|
||
"en": "Fix hands: enlarge, then fix (fallback)"
|
||
},
|
||
"about": {
|
||
"zh": "整张图放大到约 400 万像素（小图 2 倍）轻轻重画，让手变大；再把每只手放大重画后贴回去：有 SAM3 模型时先按文字找出贴着手形的轮廓重画一遍，再用手部检测框补修一遍。",
|
||
"en": "The whole picture is enlarged to about 4 megapixels (2× for a small one) and redrawn lightly, so the hands grow; then each hand is redrawn larger and pasted back: with the SAM3 model here, first inside the outline it finds by the word, then once more in the box the hand detector finds."
|
||
},
|
||
"source": {
|
||
"zh": "参考作者的「先放大重画」和「手部精修」两步合在一起，2026-10-29 在 RTX 4050 上试出这组数；SAM3 按文字找手那一轮照他的连法，2026-11-03 加入",
|
||
"en": "The reference author's light redraw after enlarging and his hand detailing, put together; these numbers tried on an RTX 4050 on 2026-10-29; the SAM3 pass finding hands by the word follows his wiring, added on 2026-11-03"
|
||
},
|
||
"packs": {
|
||
"FaceDetailer": "ComfyUI-Impact-Pack",
|
||
"UltralyticsDetectorProvider": "ComfyUI-Impact-Subpack"
|
||
},
|
||
"takes": "picture",
|
||
"detectors": {
|
||
"hand": "hand_yolov8"
|
||
},
|
||
"checkpoints": {
|
||
"sam3": "sam3"
|
||
},
|
||
"roles": {
|
||
"sampler": {
|
||
"denoise": 0.4
|
||
}
|
||
},
|
||
"nodes": {
|
||
"picture": {
|
||
"class_type": "LoadImage",
|
||
"inputs": {
|
||
"image": "$image"
|
||
}
|
||
},
|
||
"bigger": {
|
||
"class_type": "ImageScaleBy",
|
||
"inputs": {
|
||
"image": [
|
||
"picture",
|
||
0
|
||
],
|
||
"upscale_method": "lanczos",
|
||
"scale_by": "$enlarge"
|
||
}
|
||
},
|
||
"encode": {
|
||
"class_type": "VAEEncode",
|
||
"inputs": {
|
||
"pixels": [
|
||
"bigger",
|
||
0
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
]
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"hand_seeker": {
|
||
"class_type": "CheckpointLoaderSimple",
|
||
"optional": true,
|
||
"_meta": {
|
||
"title": "SAM3"
|
||
},
|
||
"inputs": {
|
||
"ckpt_name": "$sam3"
|
||
}
|
||
},
|
||
"hand_words": {
|
||
"class_type": "CLIPTextEncode",
|
||
"optional": true,
|
||
"_meta": {
|
||
"title": "SAM3: what to find"
|
||
},
|
||
"inputs": {
|
||
"text": "hand:8",
|
||
"clip": [
|
||
"hand_seeker",
|
||
1
|
||
]
|
||
}
|
||
},
|
||
"hand_shapes": {
|
||
"class_type": "SAM3_Detect",
|
||
"optional": true,
|
||
"inputs": {
|
||
"model": [
|
||
"hand_seeker",
|
||
0
|
||
],
|
||
"image": [
|
||
"$decode",
|
||
0
|
||
],
|
||
"conditioning": [
|
||
"hand_words",
|
||
0
|
||
],
|
||
"threshold": 0.5,
|
||
"refine_iterations": 2,
|
||
"individual_masks": false
|
||
}
|
||
},
|
||
"hand_areas": {
|
||
"class_type": "MaskToSEGS",
|
||
"optional": true,
|
||
"inputs": {
|
||
"mask": [
|
||
"hand_shapes",
|
||
0
|
||
],
|
||
"combined": false,
|
||
"crop_factor": 2.0,
|
||
"bbox_fill": false,
|
||
"drop_size": 10,
|
||
"contour_fill": false
|
||
}
|
||
},
|
||
"shaped_hands": {
|
||
"class_type": "DetailerForEach",
|
||
"like": "$sampler",
|
||
"optional": true,
|
||
"inputs": {
|
||
"image": [
|
||
"$decode",
|
||
0
|
||
],
|
||
"segs": [
|
||
"hand_areas",
|
||
0
|
||
],
|
||
"model": [
|
||
"$sampler.model",
|
||
"*"
|
||
],
|
||
"clip": [
|
||
"$sampler.positive.clip",
|
||
"*"
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
],
|
||
"positive": [
|
||
"$sampler.positive",
|
||
"*"
|
||
],
|
||
"negative": [
|
||
"$sampler.negative",
|
||
"*"
|
||
],
|
||
"guide_size": 768,
|
||
"max_size": 1024,
|
||
"denoise": 0.45,
|
||
"feather": 5,
|
||
"noise_mask": true,
|
||
"force_inpaint": true,
|
||
"noise_mask_feather": 10,
|
||
"wildcard": "detailed hand"
|
||
}
|
||
},
|
||
"hand_finder": {
|
||
"class_type": "UltralyticsDetectorProvider",
|
||
"inputs": {
|
||
"model_name": "$hand"
|
||
}
|
||
},
|
||
"hands": {
|
||
"class_type": "FaceDetailer",
|
||
"like": "$sampler",
|
||
"inputs": {
|
||
"image": [
|
||
"shaped_hands|$decode",
|
||
0
|
||
],
|
||
"model": [
|
||
"$sampler.model",
|
||
"*"
|
||
],
|
||
"clip": [
|
||
"$sampler.positive.clip",
|
||
"*"
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
],
|
||
"positive": [
|
||
"$sampler.positive",
|
||
"*"
|
||
],
|
||
"negative": [
|
||
"$sampler.negative",
|
||
"*"
|
||
],
|
||
"bbox_detector": [
|
||
"hand_finder",
|
||
0
|
||
],
|
||
"guide_size": 768,
|
||
"max_size": 1024,
|
||
"denoise": 0.45,
|
||
"bbox_threshold": 0.3,
|
||
"bbox_crop_factor": 2.0,
|
||
"feather": 5,
|
||
"drop_size": 10,
|
||
"wildcard": "detailed hand"
|
||
}
|
||
},
|
||
"save": {
|
||
"class_type": "SaveImage",
|
||
"inputs": {
|
||
"images": [
|
||
"hands",
|
||
"image"
|
||
],
|
||
"filename_prefix": "hands_fixed"
|
||
}
|
||
}
|
||
},
|
||
"after": "A fallback: a FLUX-Fill redraw of one square crop around each hand did better in the user's tests; use that when you have it. The picture is enlarged to about 4 megapixels (2× for one of about 1 megapixel, at most 2×, not at all for a large one) and drawn again lightly (the sampler now takes it, at denoise 0.4), then the hands are redrawn larger: with SAM3 here, first each hand it finds by the word inside its own outline (shaped_hands), then each hand the detector finds, in its box (hands, denoise 0.45), saved with prefix hands_fixed (without SAM3, which the user can get in the ways panel, only the detector's pass); the enlarged one is saved too, without the hand pass. About 3 tries in 4 gave a good hand in the pictures tried (one or two people, simple poses), no rate for crowds or hard poses: run_workflow with batch 4 (each try its own seed), then check them before the user does: zoom_image each hands_fixed picture on the hand, compare_with the enlarged one (the light redraw alone already changes faces and hands), and drop a hand with the wrong number of fingers, fused or melted fingers, one far bigger or smaller than its arm, a seam at its edge, or a hand that was fine made worse; say if a hand was missed. None good: run_workflow batch 4 again, at most twice. Then a picks panel zoomed on the hand lets the user choose among the good ones.",
|
||
"notes": "Tried on the Codex test picture (1280×832, three characters, the hand about 110×78 px): the hand pass alone gave a good hand in about half the seeds whatever its size (512 or 768) and denoise (0.45 or 0.55); enlarging 1.5× first gave good hands in 3 of 4, 2× gave sharper fingers in the same seeds (about 105 s instead of 75 s). Denoise 0.4 for the enlarged redraw kept the layout; faces and splashes change a little. The SAM3 pass (2026-11-03): its word says how many it takes, \"hand\" alone only the likeliest hand, \"hand:8\" up to eight; on a 832×1216 picture of a girl waving both hands (enlarged 2×) it outlined both hands closely at threshold 0.5 (0.2 found no more), about 112 s with both passes on Anima with the Turbo LoRA. GPT's check the same day (two people, one hand with fused fingers, two seeds): SAM3 found both hands (one outline took in the wrist), both versions gave acceptable hands; on that one picture the SAM3 pass was not shown better than the detector alone.",
|
||
"models": [
|
||
"hand_yolov8s",
|
||
"sam3_1",
|
||
"anima_turbo_lora"
|
||
],
|
||
"tested": {
|
||
"gpu": "RTX 4050 Laptop",
|
||
"vram_gb": 6,
|
||
"date": "2026-11-03",
|
||
"runs": [
|
||
{
|
||
"model": "Anima (Kirazuri v4, Turbo LoRA)",
|
||
"size": "1280×832 → 2560×1664",
|
||
"seconds": 105
|
||
},
|
||
{
|
||
"model": "Anima (MiaoMiao Harem 1.5, Turbo LoRA, SAM3 pass)",
|
||
"size": "832×1216 → 1664×2432",
|
||
"seconds": 112
|
||
}
|
||
]
|
||
},
|
||
"variants": {
|
||
"anima": {
|
||
"loras": {
|
||
"turbo": "anima-turbo-lora"
|
||
},
|
||
"without_loras": "On an Anima model the Anima Turbo LoRA (anima-turbo-lora-v0.2, the user can get it in the ways panel) makes this about three times faster: 10 steps at CFG 1.",
|
||
"roles": {
|
||
"sampler": {
|
||
"denoise": 0.4,
|
||
"steps": 10,
|
||
"cfg": 1.0,
|
||
"sampler_name": "euler_ancestral",
|
||
"scheduler": "normal"
|
||
}
|
||
},
|
||
"nodes": {
|
||
"picture": {
|
||
"class_type": "LoadImage",
|
||
"inputs": {
|
||
"image": "$image"
|
||
}
|
||
},
|
||
"turbo": {
|
||
"class_type": "LoraLoaderModelOnly",
|
||
"inputs": {
|
||
"model": [
|
||
"$sampler.model",
|
||
"*"
|
||
],
|
||
"lora_name": "$turbo",
|
||
"strength_model": 0.7
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"bigger": {
|
||
"class_type": "ImageScaleBy",
|
||
"inputs": {
|
||
"image": [
|
||
"picture",
|
||
0
|
||
],
|
||
"upscale_method": "lanczos",
|
||
"scale_by": "$enlarge"
|
||
}
|
||
},
|
||
"encode": {
|
||
"class_type": "VAEEncode",
|
||
"inputs": {
|
||
"pixels": [
|
||
"bigger",
|
||
0
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
]
|
||
},
|
||
"wire_to": "$sampler"
|
||
},
|
||
"hand_seeker": {
|
||
"class_type": "CheckpointLoaderSimple",
|
||
"optional": true,
|
||
"_meta": {
|
||
"title": "SAM3"
|
||
},
|
||
"inputs": {
|
||
"ckpt_name": "$sam3"
|
||
}
|
||
},
|
||
"hand_words": {
|
||
"class_type": "CLIPTextEncode",
|
||
"optional": true,
|
||
"_meta": {
|
||
"title": "SAM3: what to find"
|
||
},
|
||
"inputs": {
|
||
"text": "hand:8",
|
||
"clip": [
|
||
"hand_seeker",
|
||
1
|
||
]
|
||
}
|
||
},
|
||
"hand_shapes": {
|
||
"class_type": "SAM3_Detect",
|
||
"optional": true,
|
||
"inputs": {
|
||
"model": [
|
||
"hand_seeker",
|
||
0
|
||
],
|
||
"image": [
|
||
"$decode",
|
||
0
|
||
],
|
||
"conditioning": [
|
||
"hand_words",
|
||
0
|
||
],
|
||
"threshold": 0.5,
|
||
"refine_iterations": 2,
|
||
"individual_masks": false
|
||
}
|
||
},
|
||
"hand_areas": {
|
||
"class_type": "MaskToSEGS",
|
||
"optional": true,
|
||
"inputs": {
|
||
"mask": [
|
||
"hand_shapes",
|
||
0
|
||
],
|
||
"combined": false,
|
||
"crop_factor": 2.0,
|
||
"bbox_fill": false,
|
||
"drop_size": 10,
|
||
"contour_fill": false
|
||
}
|
||
},
|
||
"shaped_hands": {
|
||
"class_type": "DetailerForEach",
|
||
"like": "$sampler",
|
||
"optional": true,
|
||
"inputs": {
|
||
"image": [
|
||
"$decode",
|
||
0
|
||
],
|
||
"segs": [
|
||
"hand_areas",
|
||
0
|
||
],
|
||
"model": [
|
||
"turbo",
|
||
0
|
||
],
|
||
"clip": [
|
||
"$sampler.positive.clip",
|
||
"*"
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
],
|
||
"positive": [
|
||
"$sampler.positive",
|
||
"*"
|
||
],
|
||
"negative": [
|
||
"$sampler.negative",
|
||
"*"
|
||
],
|
||
"guide_size": 768,
|
||
"max_size": 1024,
|
||
"steps": 10,
|
||
"cfg": 1.0,
|
||
"sampler_name": "euler_ancestral",
|
||
"scheduler": "normal",
|
||
"denoise": 0.45,
|
||
"feather": 5,
|
||
"noise_mask": true,
|
||
"force_inpaint": true,
|
||
"noise_mask_feather": 10,
|
||
"wildcard": "detailed hand"
|
||
}
|
||
},
|
||
"hand_finder": {
|
||
"class_type": "UltralyticsDetectorProvider",
|
||
"inputs": {
|
||
"model_name": "$hand"
|
||
}
|
||
},
|
||
"hands": {
|
||
"class_type": "FaceDetailer",
|
||
"like": "$sampler",
|
||
"inputs": {
|
||
"image": [
|
||
"shaped_hands|$decode",
|
||
0
|
||
],
|
||
"model": [
|
||
"turbo",
|
||
0
|
||
],
|
||
"clip": [
|
||
"$sampler.positive.clip",
|
||
"*"
|
||
],
|
||
"vae": [
|
||
"$decode.vae",
|
||
"*"
|
||
],
|
||
"positive": [
|
||
"$sampler.positive",
|
||
"*"
|
||
],
|
||
"negative": [
|
||
"$sampler.negative",
|
||
"*"
|
||
],
|
||
"bbox_detector": [
|
||
"hand_finder",
|
||
0
|
||
],
|
||
"guide_size": 768,
|
||
"max_size": 1024,
|
||
"steps": 10,
|
||
"cfg": 1.0,
|
||
"sampler_name": "euler_ancestral",
|
||
"scheduler": "normal",
|
||
"denoise": 0.45,
|
||
"bbox_threshold": 0.3,
|
||
"bbox_crop_factor": 2.0,
|
||
"feather": 5,
|
||
"drop_size": 10,
|
||
"wildcard": "detailed hand"
|
||
}
|
||
},
|
||
"save": {
|
||
"class_type": "SaveImage",
|
||
"inputs": {
|
||
"images": [
|
||
"hands",
|
||
"image"
|
||
],
|
||
"filename_prefix": "hands_fixed"
|
||
}
|
||
}
|
||
},
|
||
"after": "A fallback: a FLUX-Fill redraw of one square crop around each hand did better in the user's tests; use that when you have it. On this Anima model the Anima Turbo LoRA (0.7) makes both passes 10 steps at CFG 1, about 105 s for 1280×832 (2×) on a 6 GB card. The picture is enlarged to about 4 megapixels (2× for one of about 1 megapixel, at most 2×, not at all for a large one) and drawn again lightly (the sampler now takes it, at denoise 0.4), then the hands are redrawn larger: with SAM3 here, first each hand it finds by the word inside its own outline (shaped_hands), then each hand the detector finds, in its box (hands, denoise 0.45), saved with prefix hands_fixed (without SAM3, which the user can get in the ways panel, only the detector's pass); the enlarged one is saved too, without the hand pass. About 3 tries in 4 gave a good hand in the pictures tried (one or two people, simple poses), no rate for crowds or hard poses: run_workflow with batch 4 (each try its own seed), then check them before the user does: zoom_image each hands_fixed picture on the hand, compare_with the enlarged one (the light redraw alone already changes faces and hands), and drop a hand with the wrong number of fingers, fused or melted fingers, one far bigger or smaller than its arm, a seam at its edge, or a hand that was fine made worse; say if a hand was missed. None good: run_workflow batch 4 again, at most twice. Then a picks panel zoomed on the hand lets the user choose among the good ones."
|
||
}
|
||
}
|
||
}
|