Files
8460s-image-rd/assets-library/workflows/winner_auto-illustration_auto-R2-clean-2-4-flux-dev.json
choijaewook 4282ffa8f9 meeting-103 v2.1 clean R2 5/5: PuLID 0.85+Redux 0.5 = pastel 49.99% (전체 best 갱신)
R2 5조합 (5/5 success, retry 2회 포함):
- 2-1: PuLID 0.7 + Redux 0.5 + Stage 3 Refiner (denoise 0.3) → 48.82% (Stage 3 효과 미미)
- 2-2: PuLID 0.7 + Redux 0.7 → 48.93%
- 2-3: PuLID 0.7 + Redux 0.3 → 38.52% (Redux 낮으면 파스텔 감소)
- 2-4: PuLID 0.85 + Redux 0.5 → 49.99% ★ R2 best & 전체 best
- 2-5: 한옥 spring (cherry blossom) → 44.45% / black 4.3%

R1 best (R1-4 48.5%) → R2-4 (49.99%) = +1.5 pp 갱신
R9 legacy (44.5%) → R2-4 (49.99%) = +5.5 pp 누적

학습:
- PuLID weight 0.85 + Redux 0.5 multiply 조합이 0.7/0.5 보다 우월
- Redux 0.3 너무 낮음, 0.7 비슷, 0.85+ 미검증
- Stage 3 Refiner 효과 미미 (48.5% → 48.82%, +0.3pp)

CUDA error 회복:
- 2-3, 2-4, 2-5 첫 시도 CUDA invalid argument
- ComfyUI venv 재시작 후 retry → 3/3 모두 success
- 매 ~5건 후 재시작 패턴 확인됨

자산 라이브러리:
- models-performance: 8 모델 추적
- workflows: winner_auto 4 (R1-4, R2-1, R2-2, R2-4) + partial 5
- prompts/proven: 7 패턴 (R1, R2 합산)

R3 계획:
- 3-1: PuLID 0.7 + Redux 0.85 (push redux 더 강)
- 3-2: PuLID 0.6 + Redux 0.7 (PuLID 약화)
- 3-3: PuLID 0.7 + Redux 0.7 @ 1024x1792 (해상도 증가)
- 3-4: Qwen-Image fp8 + Lightning LoRA 60갑자 (fp8 ~20G 완료, GGUF 회피)
- 3-5: Pony V6 img2img from byeolyi-ref (대안 ID 방법)

검수: D:\Vault\8460s-image-rd\eval\meeting-103-v2.1-clean-grid.html
2026-05-19 23:36:44 +09:00

210 lines
3.7 KiB
JSON

{
"1": {
"class_type": "UnetLoaderGGUF",
"inputs": {
"unet_name": "flux1-dev-Q5_K_S.gguf"
}
},
"2": {
"class_type": "DualCLIPLoader",
"inputs": {
"clip_name1": "clip_l.safetensors",
"clip_name2": "t5xxl_fp8_e4m3fn.safetensors",
"type": "flux"
}
},
"3": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "ae.safetensors"
}
},
"4": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "A 25-28 year old Korean woman in a modern hanbok with subtle Cute Horror mood, sitting gracefully in a traditional Korean tea house with hanok wooden architecture, warm afternoon light filtering through latticed windows, cool pale skin, gentle expression, photorealistic, high detail",
"clip": [
"2",
0
]
}
},
"5": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "cartoon, anime, child, teenage, purple hoodie, japanese building, plastic skin",
"clip": [
"2",
0
]
}
},
"6": {
"class_type": "EmptyLatentImage",
"inputs": {
"width": 768,
"height": 1344,
"batch_size": 1
}
},
"7": {
"class_type": "PulidFluxModelLoader",
"inputs": {
"pulid_file": "pulid_flux_v0.9.1.safetensors"
}
},
"8": {
"class_type": "PulidFluxEvaClipLoader",
"inputs": {}
},
"9": {
"class_type": "PulidFluxInsightFaceLoader",
"inputs": {
"provider": "CUDA"
}
},
"10": {
"class_type": "LoadImage",
"inputs": {
"image": "byeolyi-ref-768x1344.png"
}
},
"11": {
"class_type": "ApplyPulidFlux",
"inputs": {
"model": [
"1",
0
],
"pulid_flux": [
"7",
0
],
"eva_clip": [
"8",
0
],
"face_analysis": [
"9",
0
],
"image": [
"10",
0
],
"weight": 0.85,
"start_at": 0.0,
"end_at": 0.8,
"fusion": "mean",
"fusion_weight_max": 1.0,
"fusion_weight_min": 0.0,
"train_step": 1000,
"use_gray": true
}
},
"12": {
"class_type": "FluxGuidance",
"inputs": {
"conditioning": [
"19",
0
],
"guidance": 3.5
}
},
"13": {
"class_type": "KSampler",
"inputs": {
"model": [
"11",
0
],
"positive": [
"12",
0
],
"negative": [
"5",
0
],
"latent_image": [
"6",
0
],
"seed": 102004,
"steps": 25,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"denoise": 1.0
}
},
"14": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"13",
0
],
"vae": [
"3",
0
]
}
},
"15": {
"class_type": "SaveImage",
"inputs": {
"images": [
"14",
0
],
"filename_prefix": "m103_clean_r2_4_pulid085_redux05"
}
},
"16": {
"class_type": "StyleModelLoader",
"inputs": {
"style_model_name": "flux1-redux-dev.safetensors"
}
},
"17": {
"class_type": "CLIPVisionLoader",
"inputs": {
"clip_name": "sigclip_vision_patch14_384.safetensors"
}
},
"18": {
"class_type": "CLIPVisionEncode",
"inputs": {
"clip_vision": [
"17",
0
],
"image": [
"10",
0
],
"crop": "center"
}
},
"19": {
"class_type": "StyleModelApply",
"inputs": {
"conditioning": [
"4",
0
],
"style_model": [
"16",
0
],
"clip_vision_output": [
"18",
0
],
"strength": 0.5,
"strength_type": "multiply"
}
}
}