Xibalba - Dark Fantasy Witch & Occult Sigils
12st · euler 768×1152 8GB
Full Resolution
Generation Specs RTX 4070
Sampler euler
Scheduler simple
Steps 8
CFG Scale 1
Seed 1479435414
Target VRAM 12GB
VRAM 8GB - 12GB
GPU Hardware Compatibility
Optimal Ground Truth
Native GPU execution at full throughput with zero memory swapping.
Krea 2 Turbo (Official Comfy-Org) Civitai #144286898 Min 8GB VRAM 768×1376 RTX 4070 Verified
Academic Classical Veil - Neoclassical Muse & Weathered Patina
High-fashion fine art portrait blending Academic classicism and medium-format editorial photography with semi-sheer noir chiffon drapery, antique weathered wood, and golden-hour chiaroscuro lighting.
Blueprint Summary RTX 4070 Verified
Reproducible ComfyUI workflow for Civitai #144286898: Academic Classical Veil - Neoclassical Muse & Weathered Patina using Krea 2 Turbo (Official Comfy-Org) at 768×1376 resolution. Requires minimum 8GB VRAM with sampler euler and scheduler simple (8 steps). Includes 1-click terminal model sync and canvas JSON graph.
Node Graph Pipeline 14 Total Nodes
Verify in Resolver 01 Load Models
UNETLoader
7 loaders (DiT, CLIP, VAE)
02 Adapters
LoraLoader
4 adapters
03 Conditioning
CLIPTextEncode
3 prompt encodings
04 KSampler
KSampler
DiT latent denoising
05 Decode & Save
VAEDecode
Latent to pixel space
Execution DAG Topology Interactive Visualizer
Drag to pan · Scroll to zoom · Hover wiresModel & Asset Setup 1-Click Script
Run in your ComfyUI root:
curl -fsSL https://decomfy.com/api/scripts/civitai-classical-veil-krea2.sh | bash Loading bash setup script... Loading PowerShell setup script... import modal
app = modal.App("comfyui-civitai-classical-veil-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 #144286898: Academic Classical Veil - Neoclassical Muse & Weathered Patina on ephemeral T4 GPU...")
return {"status": "success", "slug": "civitai-classical-veil-krea2"}
runpodctl create pod \
--name "comfy-civitai-classical-veil-krea2" \
--gpu-type "NVIDIA RTX 4070 Ti" \
--image "runpod/comfyui:latest" \
--volume-in-gb 50 \
--ports "8188/http" # ComfyUI Model Batch Ingestion for Civitai #144286898: Academic Classical Veil - Neoclassical Muse & Weathered Patina
# Run with: aria2c -i models-civitai-classical-veil-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/YARN_MetArt.safetensors
dir=models/loras
out=YARN_MetArt.safetensors
https://huggingface.co/hoangyellcom/decomfy-loras/resolve/main/loras/ImpressionismKrea2Raw.safetensors
dir=models/loras
out=ImpressionismKrea2Raw.safetensors
https://huggingface.co/hoangyellcom/decomfy-loras/resolve/main/loras/breast_size_v2_krea2_loraholic.safetensors
dir=models/loras
out=breast_size_v2_krea2_loraholic.safetensors
https://huggingface.co/hoangyellcom/decomfy-loras/resolve/main/loras/TeeKaysTittyTime_AQueensTits_V1-3_Kr2.safetensors
dir=models/loras
out=TeeKaysTittyTime_AQueensTits_V1-3_Kr2.safetensors Positive Prompt
High-fashion fine art portrait, neoclassical muse with long curly honey-golden hair cascading softly over shoulders, wearing an elegant opaque black velvet evening gown with high neckline and delicate sheer chiffon shawl, standing beside an antique, heavily weathered white painted rustic door with organic peeling texture and rich wood grain. Soft golden hour Rembrandt side lighting casting delicate chiaroscuro gradients, luminous natural skin tones, creamy optical bokeh. Shot on Hasselblad X2D 100C with 65mm lens at f/1.8, sophisticated Vogue Italia editorial, museum fine-art oil painting aesthetic blended with ultra-realistic medium format photography, quiet contemplative mood, masterpiece composition, fully clothed, modest elegant fashion.
Negative Prompt
bare skin on chest, exposed breasts, nipples, topless, naked, nude, cleavage, navel, stomach, underage, lowres, blurry, bad anatomy, deformed hands, extra fingers, low quality, artifacts, distorted proportions, text, watermark
LoRA Adapter Stack 4 Adapters
RTX 4070 Calibrated Weights 01 The YARN Collection for Krea2 +0.8
02 Impressionism +0.9
03 Breast Size Slider - (Krea-2 + ZIT) -1.8
04 A Queen's Breasts | Krea2 +1
Required Models 7 Models
krea2_turbo_int8_convrot.safetensors Official Krea 2 Turbo INT8 ConvRot Diffusion Transformer core
qwen3vl_4b_fp8_scaled.safetensors Official Qwen3-VL 4B FP8 Scaled Text Encoder (CLIPLoader type: krea2)
qwen_image_vae.safetensors Official 16-channel Video & Image VAE
YARN_MetArt.safetensors Weight: 0.8 (The YARN Collection for Krea2 - MetArt aesthetic)
ImpressionismKrea2Raw.safetensors Weight: 0.9 (Impressionism brushwork and atmospheric lighting)
breast_size_v2_krea2_loraholic.safetensors Weight: -1.8 (Upper body volumetric slider)
TeeKaysTittyTime_AQueensTits_V1-3_Kr2.safetensors Weight: 1.0 (Anatomical sculpture contour)
Field Notes RTX 4070 Benchmark
Benchmark: Rendered on NVIDIA GeForce RTX 4070 (INT8 CPU-offload patch)
Academic classicism aesthetic on Krea 2 Turbo DiT with MetArt YARN fine-art textures, Impressionism brushwork, and dual-prompt ComfyUI canvas architecture.
Frequently Asked Questions FAQ
What GPU and VRAM are required to run Civitai #144286898: Academic Classical Veil - Neoclassical Muse & Weathered Patina?
This workflow requires a minimum of 8GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at 768x1376 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.
Related ComfyUI Blueprints
View all 31 workflows
Inari Fox Shrine: Torii Twilight & Dynamic Cel Shading
8st · euler 672×1176 8GB
Snow White Window: Arched Sunlight & Porcelain Film Aesthetics
8st · euler 832×1152 10GB