Character Unwrapper & Outfit on Ground

Workflows are embedded in all preview images

Input a female character single full-body image to automatically unwrap character clothing, seamlessly generate dropped garments flat-lay on the ground, and upscale to 2MP.

V0.3

Organized and structured nodes into Subgraphs

1. A recommanded approach is：

   1. first enable '4 - Optional - Auto Gen Assets' and disable Group 5,6 and '4 - Optional - Manual Load Assets', to first generate clothing/shoe images that meet the standards,

   2. then disable '4 - Optional - Auto Gen Assets' , enable '4 - Optional - Manual Load Assets' to load the generated images into it, and enable Group 5 and 6 to composite.

2. Because of not wanting to use VLM, I made lots of IF/Else judgments, which actually increased the process of the Workflow. The next version plans to use VLM.

Model

• Qwen Image 2.1 - Comfy-Org/Qwen-Image-2.1

• Krea2 - Moody Krea 2 Mix V8

• Qwen - Phr00t/Qwen-Image-Edit-Rapid-AIO

  • └ INT8 Convrot/INT6 W6A8 Conversion(19G/14.9G):

    • HuggingFace - waveshaker/comfy_models/qwen

    • Civitai - QWEN RAPID NSFW v23 - INT8 Convrot/INT6 W6A8

• Flux2 Klein 9B - Moody Desire Mix v3.0

  • └ INT8 Convrot Conversion - moodyDesireMix_v30_fp16_ctq_int8_convrot.safetensors

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 sam3/
│      ├── 📄 sam3.pt

• SAM3(Official: FP32) - facebook/sam3

  • └ FP16/Mixed FP8/FP8 version:

    • HuggingFace - waveshaker/comfy_models/sam3

    • Civitai - SAM3 - FP16/Mixed FP8/FP8

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 checkpoints/

• SAM3.1 - Comfy-Org/sam3.1

  • └ INT8 Convrot Conversion - SAM 3.1 INT8 + INT4 Native ConvRot

YOLO Detection Models

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 ultralytics/

• foot-yolov8l.pt

• HeelsDetect Y8m.pt

LoRA

• Flux 2 Klein 9B

  • f2k_9B_lcs_consist_20260415 - Consistence Edit Lora

• Krea2

  • HighQuality - High resolution

• Qwen Image 2.1

  • qwen-image-2.1-outpaint-v2 - Qwen Image 2.1 Outpaint LoRA — Extend Any Side

V0.2

early draft.