Input a single full-body image, auto-upscale it to high resolution(2MP), and generate a multi-view showcase grid focusing on face, legs, and feet details seamlessly, good for Character LoRA dataset preparation.
V1.2
1. Flow Control: To avoid frequent model switching, loading, and unloading, added a Preprocess pipeline to obtain masks ahead of time.
2. Batch Image Processing: Organized and structured nodes into Subgraphs, and modified Face/Legs/Feet into Batch Image processing based on model types (Qwen/K9B/Krea2) step-by-step, improving processing speed.
Models
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
INT6 is just a bit slower than INT8 (about 33s vs 30s), but the model size is smaller and the results are pretty much the same.
Flux2 Klein 9B - Moody Desire Mix v3.0
└ INT8 Convrot Conversion - moodyDesireMix_v30_fp16_ctq_int8_convrot.safetensors
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 sam3/
│ ├── 📄 sam3.ptSAM3(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/LoRA
Krea2
HighQuality - High resolution
Qwen
Qwen-Image-Edit-2511-Unblur-Upscale - Qwen-Image-Edit-Unblur-Upscale_20.safetensors
Flux 2 Klein 9B
f2k_9B_lcs_consist_20260415 - Consistence Edit Lora
V1.1
Fully replaced SAM3 Segmentation (RMBG) with comfyui-easy-sam3, resolving the OOM issue caused by the RMBG SAM3 failing to clear VRAM.
Added a toggleable Krea 2 refine step into every original Upscale step; Krea 2 enhances skin realism.
Note: There is nothing wrong with the quality of the RMBG custom node itself, and SAM3 Segmentation (RMBG) does provide a model unloading option. However, when the workflow requires heavy and frequent use of it to generate masks, the model unloading speed of RMBG's SAM3 Segmentation is too slow, which increases the total workflow execution time.
V1.0
⚠️ VRAM Notice: SAM3 Segmentation (RMBG) in the RMBG custom node currently causes VRAM OOM issues.
Please use either comfyui-easy-sam3 (with sam3.pt) or ComfyUI native SAM3 Detect (with SAM3.1) instead. Alternatively, I'll release a fixed version soon.The new version will use Krea2 for more realistic skin texture.
Description
FAQ
Comments (4)
Can I improve the hair quality with this workflow? I’ve been using Krea2 to generate images of my model, but the hair quality isn't that great; there’s a noticeable, somewhat plastic-like texture when you look closely.
This workflow processes the hair through a reference-less refine using K9B with hair mask, then followed by an overall upscale using KR2. You can fine-tune the hair details by adjusting the denoise parameter in the K9BHairUpscaler subgraph, as well as the BlurSize for the hair mask .
@rogerpie Ok, thanks
@Acara For the hair region of highly blurred images, the editing-mode restoration capabilities of Qwen and Klein9B (with reference) are extremely poor. While Qwen has a strong ability to restore facial features, it struggles with hair; meanwhile, Klein9B only makes already-clear pictures sharper and performs poorly on blurry inputs.
To solve this, after completing the Qwen and Klein9B stage, K9BHairUpscaler is applied to the K9B output image's hair mask region with a low denoising strength to generate similarly colored hair. This part's output is then passed to Krea2, where the workflow continues using a low denoising strength to optimize both the skin and hair,while bypassing the face entirely to preserve the previously restored facial features.
The overall head restoration workflow sequence is :
QwenRestorer -> Qwen_Output: [face, feet] ->
K9BUpscaler -> K9B_Output: [face -> K9BHairUpsclaer -> output, legs, feet] ->
KR2SkinDetailer -> KR2_Output: [face, legs, feet] ->
ColorFixer -> Next Stage
Note: The K9BHairUpscaler can be dynamically bypassed via the Controller