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
⚠️ 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.
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.
Models
Qwen - Phr00t/Qwen-Image-Edit-Rapid-AIO
└ INT8 Conversion - Qwen-Rapid-AIO-NSFW-v23_diffusion_only_fp8-int8_convrot.safetensors
Flux2 Klein 9B - Moody Desire Mix v3.0
└ INT8 Conversion - moodyDesireMix_v30_fp16_ctq_int8_convrot.safetensors
SAM3.1 - Comfy-Org/sam3.1
Detection Models
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 ultralytics/📂 ComfyUI/
├── 📂 models/
│ ├── 📂 sam3/LoRA
Flux 2 Klein 9B
f2k_9B_lcs_consist_20260415 - Consistence Edit Lora
FAQ
Comments (8)
Hi any reason why you did not just use the stock seedvr2 model location and loader. The KJ loader and model locations makes things messy on local folders dropping links and getting the workflow to load Seedvr2 a PITA.
You're totally right. The workflow just reflects my personal model management habits. Feel free to swap in your preferred SeedVR Upscale workflow.
I actually just updated the workflow and removed SeedVR entirely because:
1. After the Qwen/Klein 9B upscale, SeedVR adds almost no visual improvement but significantly slows down the workflow.
2. SeedVR was causing VRAM OOM issues for some users.
@rogerpie Thanks for the quick reply. I have only been playing with comfy for about a year but seems to me that almost all of these detailers and upscalers are pretty dated? Diffusion models and loras come out like a machine gun so fast you can't track them all but most of these "refinement" assets seem to be from 2022. In my experience with SeedVR2 anytime you come anywhere near an NSFW area the skin goes all plastic anyway. Basically anything beyond faces and hands.
@markfjohnson
I think the details of the lips and pEn-is in SeedVR are terrible. However, sometimes, even though the visual changes brought by SeedVR are minimal, there might be a change in the pixel space (perhaps a subtle sharpening), which actually turns out to be beneficial for next step processing with the image model. In this workflow, if you don't use SeedVR for upscaling the shoes, the next step's Klein 9B easily renders the transparent straps of the clear high heels as brownish-yellow tape, whereas using SeedVR upscaling greatly reduces this tendency.
moodyDesireMix_v30_fp16_ctq_flux2_int8_convrot.safetensor
Qwen-Rapid-AIO-NSFW-v23_diffusion_only-int8_convrot.safetensors
Where can I download them?
I converted these myself using comfyui-starnodes-modelconverter. You can grab the original models and convert them locally on your own, or wait about 30 minutes — I'm currently uploading them to HuggingFace.
thanks:)