Civitai #144295631 Carpet Selfie: Low-Angle Mirror Reflection & Shag Rug

Full Resolution

Generation Specs RTX 4070

Sampler euler

Scheduler simple

Steps 9

CFG Scale 1

Seed 8472910452

Target VRAM 12GB

VRAM 10GB - 12GB

GPU Hardware Compatibility

Optimal Ground Truth

Native GPU execution at full throughput with zero memory swapping.

Krea 2 Turbo (Qwen3-VL 4B + Wan 2.1 16-ch VAE) Civitai #144295631 Min 10GB VRAM 832×1152 RTX 4070 Verified

Carpet Selfie: Low-Angle Mirror Reflection & Shag Rug

Production reproduction of Civitai Red trending artwork #144295631. Authentic low-angle bedroom mirror selfie on fluffy shag rug with soft gray knit sweater and delicate eye reflections.

Blueprint Summary RTX 4070 Verified

Reproducible ComfyUI workflow for Civitai #144295631 Carpet Selfie: Low-Angle Mirror Reflection & Shag Rug using Krea 2 Turbo (Qwen3-VL 4B + Wan 2.1 16-ch VAE) at 832×1152 resolution. Requires minimum 10GB VRAM with sampler euler and scheduler simple (9 steps). Includes 1-click terminal model sync and canvas JSON graph.

Node Graph Pipeline 11 Total Nodes

Verify in Resolver

01 Load Models

UNETLoader

5 loaders (DiT, CLIP, VAE)

02 Adapters

LoraLoader

2 adapters

03 Conditioning

CLIPTextEncode

2 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 wires

Model & Asset Setup 1-Click Script

Run in your ComfyUI root:

curl -fsSL https://decomfy.com/api/scripts/civitai-carpet-mirror-selfie-krea2.sh | bash

Positive Prompt

An amateur iPhone photograph of a charming and beautiful 20-year-old woman, she takes a low-angle mirror selfie while reclining casually on a fluffy beige bedroom carpet. Natural morning window bounce light, cozy soft gray oversized sweater, candid lifestyle photography, authentic smartphone camera sensor, 8k resolution.

Negative Prompt

underage, child, glossy, airbrushed, cartoon, 3d render, plastic, fake, bad eyes, extra fingers

LoRA Adapter Stack 2 Adapters

RTX 4070 Calibrated Weights

01 nicegirls_krea2.safetensors +0.8

02 Detailer-KREA2.safetensors +0.7

Required Models 5 Models

Disk Space Required: 17.6 GB (5 models · DiT/Base: 12.8 GB · Text Encoder: 4.4 GB · LoRAs: 126 MB · VAE: 254 MB)

models/diffusion_models/ 12.8 GB Civitai

BSSDesirexKrea2_x2INT8ConvrotFastest.safetensors DesireX Krea2 INT8 ConvRot fastest quantized DiT core

Get

models/text_encoders/ 4.4 GB HuggingFace

krea2_solordz_te_int8.safetensors Qwen3-VL 4B INT8 Text Encoder (Krea 2 Architecture)

Get

models/vae/ 254 MB HuggingFace

wan_2.1_vae.safetensors 16-channel VAE (prevents inverted contrast artifacts)

Get

models/loras/ 114 MB Civitai

nicegirls_krea2.safetensors Weight: 0.8 (Natural facial features and graceful expression)

Get

models/loras/ 11.5 MB Civitai

Detailer-KREA2.safetensors Weight: 0.7 (Micro skin pores & volumetric hair curl detail)

Get

Field Notes RTX 4070 Benchmark

Benchmark: [object Object]

Reproduction of Civitai Red trending artwork #144295631. Captures extreme close-up eye reflections and realistic knit fiber tactile micro-texture.

Frequently Asked Questions FAQ

What GPU and VRAM are required to run Civitai #144295631 Carpet Selfie: Low-Angle Mirror Reflection & Shag Rug?

This workflow requires a minimum of 10GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at 832x1152 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.