Runs entirely in VRAM with no memory swapping.
Korean Steam Sauna Portrait - BloomGirls & Krea 2 Turbo
Candid Korean spa portrait featuring dewy glass skin, relaxed cedar sauna aesthetics, and soft golden rim lighting on Krea 2 Turbo.
Reproducible ComfyUI workflow for Civitai #144970991: Korean Steam Sauna Portrait - BloomGirls & Krea 2 Turbo using Krea 2 Turbo (Official Comfy-Org) at 832×1248 resolution. Requires minimum 8GB VRAM with sampler euler and scheduler simple (10 steps). Includes 1-click terminal model sync and canvas JSON graph.
Execution DAG Topology Interactive Visualizer
Drag to pan · Scroll to zoom · Hover wiresModel & Asset Setup Setup Script
Run in your ComfyUI root:
curl -fsSL https://decomfy.com/api/scripts/civitai-steam-lounge-portrait-krea2.sh | bash Loading bash setup script... Loading PowerShell setup script... import modal
app = modal.App("comfyui-civitai-steam-lounge-portrait-krea2")
vol = modal.Volume.from_name("comfy-weights-cache", create_if_missing=True)
image = (
modal.Image.debian_slim(python_version="3.11")
.apt_install("git", "wget", "curl", "libgl1-mesa-glx", "libglib2.0-0")
.pip_install("torch", "torchvision", "--index-url", "https://download.pytorch.org/whl/cu124")
.pip_install("transformers", "accelerate", "safetensors", "aiohttp")
.run_commands(
"git clone https://github.com/comfyanonymous/ComfyUI.git /root/ComfyUI",
"cd /root/ComfyUI && pip install -r requirements.txt",
)
)
@app.function(
gpu="T4",
image=image,
volumes={"/root/ComfyUI/models": vol},
timeout=900,
)
def generate():
# Headless serverless execution for Krea 2 Turbo (Official Comfy-Org)
print("Executing Civitai #144970991: Korean Steam Sauna Portrait - BloomGirls & Krea 2 Turbo on ephemeral T4 GPU...")
return {"status": "success", "slug": "civitai-steam-lounge-portrait-krea2"}
runpodctl create pod \
--name "comfy-civitai-steam-lounge-portrait-krea2" \
--gpu-type "NVIDIA RTX 4070 Ti" \
--image "runpod/comfyui:latest" \
--volume-in-gb 50 \
--ports "8188/http" # ComfyUI Model Batch Ingestion for Civitai #144970991: Korean Steam Sauna Portrait - BloomGirls & Krea 2 Turbo
# Run with: aria2c -i models-civitai-steam-lounge-portrait-krea2.txt -j4 -x4
https://huggingface.co/Comfy-Org/Krea-2/resolve/main/diffusion_models/krea2_turbo_int8_convrot.safetensors
dir=models/diffusion_models
out=krea2_turbo_int8_convrot.safetensors
https://huggingface.co/Comfy-Org/Krea-2/resolve/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors
dir=models/text_encoders
out=qwen3vl_4b_fp8_scaled.safetensors
https://huggingface.co/Comfy-Org/Krea-2/resolve/main/vae/qwen_image_vae.safetensors
dir=models/vae
out=qwen_image_vae.safetensors
https://huggingface.co/hoangyellcom/decomfy-loras/resolve/main/loras/krea2-bloomgirls-realism-step00004000.safetensors
dir=models/loras
out=krea2-bloomgirls-realism-step00004000.safetensors
https://huggingface.co/hoangyellcom/decomfy-loras/resolve/main/loras/Famegrid-Natural-V1-Krea-2.safetensors
dir=models/loras
out=Famegrid-Natural-V1-Krea-2.safetensors Positive Prompt
Negative Prompt
LoRA Adapter Stack 2 Adapters
RTX 4070 Calibrated WeightsRequired Models 5 Models
Field Notes RTX 4070 Benchmark
Frequently Asked Questions FAQ
What GPU and VRAM are required to run Civitai #144970991: Korean Steam Sauna Portrait - BloomGirls & Krea 2 Turbo?
This workflow requires a minimum of 8GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at 832x1248 resolution.
How do I resolve missing custom nodes for this workflow?
You can drop the workflow JSON into our client-side Missing Node Auto-Resolver at https://decomfy.com/resolve/ to detect missing nodes and generate install commands, or run the 1-click terminal setup script provided below.
Which VAE and conditioning text encoders are required for Krea 2 DiT?
Krea 2 DiT single-stream models strictly require the 16-channel Wan2.1 VAE and Qwen3-VL text encoder. Using standard Flux or SDXL VAE causes inverted checkerboard artifacts. Also pair with RescaleCFG for high-contrast portrait clarity.