Morning Bed Selfie - Overhead Candid & Krea 2 Turbo
10st · euler 1024×1024 8GB
Full Resolution
Generation Specs RTX 4070
Sampler euler_ancestral
Scheduler normal
Steps 20
CFG Scale 4.05
Seed 4163025414
Target VRAM 12GB
VRAM 8GB - 12GB
GPU Hardware Compatibility
Optimal Ground Truth
Native GPU execution at full throughput with zero memory swapping.
NaughtyMouseMix V10 (Illustrious-XL) Civitai #143395328 Min 8GB VRAM 1216×832 RTX 4070 Verified
Afternoon Chesterfield Lounge - Sun-Drenched Cel Shading & Modern Anime Render
Sun-drenched anime lookbook illustration rendered with Illustrious-XL and NaughtyMouseMix V10. Chains Frostbite Artstyle with Modern Anime Render for clean cel shading line art and high-contrast interior lighting.
Blueprint Summary RTX 4070 Verified
Reproducible ComfyUI workflow for Civitai #143395328: Afternoon Chesterfield Lounge - Sun-Drenched Cel Shading & Modern Anime Render using NaughtyMouseMix V10 (Illustrious-XL) at 1216×832 resolution. Requires minimum 8GB VRAM with sampler euler_ancestral and scheduler normal (20 steps). Includes 1-click terminal model sync and canvas JSON graph.
Node Graph Pipeline 11 Total Nodes
Verify in Resolver 01 Load Models
CheckpointLoaderSimple
3 loaders (DiT, CLIP, VAE)
02 Adapters
LoraLoader
2 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-chesterfield-afternoon-illustrious.sh | bash Loading bash setup script... Loading PowerShell setup script... import modal
app = modal.App("comfyui-civitai-chesterfield-afternoon-illustrious")
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 NaughtyMouseMix V10 (Illustrious-XL)
print("Executing Civitai #143395328: Afternoon Chesterfield Lounge - Sun-Drenched Cel Shading & Modern Anime Render on ephemeral T4 GPU...")
return {"status": "success", "slug": "civitai-chesterfield-afternoon-illustrious"}
runpodctl create pod \
--name "comfy-civitai-chesterfield-afternoon-illustrious" \
--gpu-type "NVIDIA RTX 4070 Ti" \
--image "runpod/comfyui:latest" \
--volume-in-gb 50 \
--ports "8188/http" # ComfyUI Model Batch Ingestion for Civitai #143395328: Afternoon Chesterfield Lounge - Sun-Drenched Cel Shading & Modern Anime Render
# Run with: aria2c -i models-civitai-chesterfield-afternoon-illustrious.txt -j4 -x4
https://civitai.com/api/download/models/2907147
dir=models/checkpoints
out=naughtymousemixV10_v10.safetensors
https://civitai.com/api/download/models/2432866
dir=models/loras
out=FrostbiteStudiov2_ArtStyle_Illu_Dwnsty.safetensors
https://civitai.com/api/download/models/2442886
dir=models/loras
out=Modern_anime_render.safetensors Positive Prompt
Score_9, score_8_up, score_7_up, score_6_up, (cel shading:1.3), (clean line art:1.5), bold outlines, 2d illustration, absurdres, realistic proportions, perfect body proportions, masterpiece, masterwork, finely drawn, intricate details, 8k, perfect scene proportion, 1girl, solo, relaxing on sofa, straight brunette hair, long braid cascading down back, wearing elegant white ribbed loungewear, soft silk shorts, slender silhouette, serene peaceful expression, reclining comfortably on a large light-grey Chesterfield sofa, soft draped grey throw blanket, wooden floor, thick light grey carpet, minimalist modern living room, white walls, sun-drenched afternoon, golden sunlight streaming through sheer curtains, deep shadows, chiaroscuro, cinematic lighting, warm ambient glow
Negative Prompt
watermark, signature, text, subtitles, letterbox, split screen, bad hands, poorly drawn hands, missing fingers, extra fingers, animal ears, tail, white border, monochrome, patreon, lowres, (worst quality, bad quality, low quality:1.2), bad eyes, poorly drawn, bad anatomy, extra arms, extra hands, extra legs, deformed limbs, glossy skin, bad scene proportions
Custom Prompt Freedom:
This workflow is 100% pre-wired. The canvas includes a secondary standby conditioning node (muted
mode: 2). When importing into ComfyUI, you can unmute it or freely write any custom prompt, characters, or aesthetic styles. The underlying model checkpoint, LoRA adapter stack, and sampling pipeline will faithfully execute your vision.
LoRA Adapter Stack 2 Adapters
RTX 4070 Calibrated Weights 01 Frostbite | Artstyle (Illustrious V2.0) +0.3
02 Modern anime render +0.1
Required Models 3 Models
naughtymousemixV10_v10.safetensors Base Checkpoint: Illustrious-XL fine-tuned for high-contrast anime aesthetics and clean cel shading
FrostbiteStudiov2_ArtStyle_Illu_Dwnsty.safetensors Weight: 0.3 (Frostbite Artstyle LoRA enforcing crisp line art, distinct silhouette clarity, and disciplined cel shading)
Modern_anime_render.safetensors Weight: 0.1 (Modern Anime Render LoRA introducing subtle rim lighting and contemporary digital styling)
Field Notes RTX 4070 Benchmark
Benchmark: Rendered on NVIDIA GeForce RTX 4070 (12GB VRAM, CUDA 12.4)
1. ARCHITECTURAL REASONING & LORA SEQUENCING PHILOSOPHY:
This workflow demonstrates precision stylistic tuning on top of Illustrious-XL using two chained LoRAs at subtle weights. Frostbite Artstyle (0.3) enforces crisp line art, distinct silhouette clarity, and disciplined cel-shading separation without overpowering the base checkpoint anatomy. Modern Anime Render (0.1) introduces micro-details, subtle rim lighting, and a modern digital illustration palette.
2. CABLE TOPOLOGY & PROMPT CONDITIONING:
Model and CLIP conditioning stream sequentially from CheckpointLoaderSimple through both LoraLoader nodes. A CLIPSetLastLayer node enforces clip_skip 2 (stop_at_clip_layer: -2), critical for Illustrious-XL text comprehension. Dual prompt conditioning nodes are provided: Node A serves as the active, sanitized lookbook prompt, while Node B (Standby, muted mode: 2) preserves the original creator prompt for 1-click local cable swapping.
3. HARDWARE BENCHMARKS & MEMORY PROFILE:
Tested on NVIDIA GeForce RTX 4070 (12GB VRAM). Illustrious-XL combined with 2 LoRAs executes 20 steps at 1216x832 in ~40 seconds with zero disk thrashing and peak VRAM well under 7.5GB.
Frequently Asked Questions FAQ
What GPU and VRAM are required to run Civitai #143395328: Afternoon Chesterfield Lounge - Sun-Drenched Cel Shading & Modern Anime Render?
This workflow requires a minimum of 8GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at 1216x832 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.
What text encoders and VAE does Qwen-Image 2.1 Uncensored require?
Qwen-Image 2.1 Uncensored uses GGUF Q4_K_M quantized DiT weights paired with the Heretic uncensored text encoder, bypassing safety refusals while maintaining precise prompt adherence.
Related ComfyUI Blueprints
View all 38 workflows
Smartphone POV Candid - Night Market Viewfinder & Krea 2 Turbo
10st · euler 1248×832 8GB
Bedroom Candid Snapshot - Realistic Flash Photography & Krea 2 Turbo
10st · euler 832×1248 8GB