Academic Classical Veil - Neoclassical Muse & Weathered Patina
8st · euler 768×1376 8GB
Full Resolution
Generation Specs RTX 4070
Sampler euler
Scheduler simple
Steps 12
CFG Scale 1
Seed 1234491987
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 #144587294 Min 8GB VRAM 768×1152 RTX 4070 Verified
Xibalba - Dark Fantasy Witch & Occult Sigils
Minimalist dark fantasy poster art styled with thick painterly strokes, high-contrast crimson skies, and an occult subterranean magic circle etched with glowing red sigils.
Blueprint Summary RTX 4070 Verified
Reproducible ComfyUI workflow for Civitai #144587294: Xibalba - Dark Fantasy Witch & Occult Sigils using Krea 2 Turbo (Official Comfy-Org) at 768×1152 resolution. Requires minimum 8GB VRAM with sampler euler and scheduler simple (12 steps). Includes 1-click terminal model sync and canvas JSON graph.
Node Graph Pipeline 13 Total Nodes
Verify in Resolver 01 Load Models
UNETLoader
6 loaders (DiT, CLIP, VAE)
02 Adapters
LoraLoader
3 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-xibalba-dark-fantasy-krea2.sh | bash Loading bash setup script... Loading PowerShell setup script... import modal
app = modal.App("comfyui-civitai-xibalba-dark-fantasy-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 #144587294: Xibalba - Dark Fantasy Witch & Occult Sigils on ephemeral T4 GPU...")
return {"status": "success", "slug": "civitai-xibalba-dark-fantasy-krea2"}
runpodctl create pod \
--name "comfy-civitai-xibalba-dark-fantasy-krea2" \
--gpu-type "NVIDIA RTX 4070 Ti" \
--image "runpod/comfyui:latest" \
--volume-in-gb 50 \
--ports "8188/http" # ComfyUI Model Batch Ingestion for Civitai #144587294: Xibalba - Dark Fantasy Witch & Occult Sigils
# Run with: aria2c -i models-civitai-xibalba-dark-fantasy-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/refusal_reduction_v2_full_rank.safetensors
dir=models/loras
out=refusal_reduction_v2_full_rank.safetensors
https://huggingface.co/hoangyellcom/decomfy-loras/resolve/main/loras/CARAPACE777_v1.safetensors
dir=models/loras
out=CARAPACE777_v1.safetensors
https://huggingface.co/hoangyellcom/decomfy-loras/resolve/main/loras/krea2_koukouya_sytle_c1-st3000.safetensors
dir=models/loras
out=krea2_koukouya_sytle_c1-st3000.safetensors Positive Prompt
XIBALBA, The painting style is highly textured, with thick, brush-like strokes and a rough, gritty quality. extremely intricate linework, monochromatic colors contrasts, bold accent colors, extreme ink hatching, crosshatching, surreal, minimalist dark fantasy illustration depicts a tiny, solitary figure standing atop a dark, underground mound etched with glowing red sigils, set against a stark, high-contrast crimson background. The artwork features flat vector shapes, organic tendril forms, esoteric symbolism, and a striking three-tone color scheme dominated by saturated crimson red, textured charcoal black, and a single accent of bright white.
Negative Prompt
blurry, ugly, distorted, low quality, oversaturated noise, jpeg artifacts, extra limbs, bad anatomy, deformed eyes
LoRA Adapter Stack 3 Adapters
RTX 4070 Calibrated Weights 01 //CARAPACE777// +1
02 画风 こうこうや koukouya style 【krea2】 +0.7
03 Krea2 TextFusion Refusal-Reduction LoRA (Updated) +1
Required Models 6 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
refusal_reduction_v2_full_rank.safetensors Weight: 1.0 (Krea2 TextFusion Refusal-Reduction LoRA)
CARAPACE777_v1.safetensors Weight: 1.0 (//CARAPACE777// dark surrealist bio-mutation aesthetic)
krea2_koukouya_sytle_c1-st3000.safetensors Weight: 0.7 (画风 こうこうや koukouya style dark anime linework & crimson mood)
Field Notes RTX 4070 Benchmark
Benchmark: Rendered on NVIDIA GeForce RTX 4070 (INT8 CPU-offload patch)
Minimalist graphic dark fantasy illustration using Krea 2 Turbo DiT with Carapace777 bio-mutation and Koukouya crimson ink styles.
Frequently Asked Questions FAQ
What GPU and VRAM are required to run Civitai #144587294: Xibalba - Dark Fantasy Witch & Occult Sigils?
This workflow requires a minimum of 8GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at 768x1152 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