Civitai #143363839 Freya Lace Boudoir: Krea 2 Photorealism Recipe

Full Resolution

Generation Specs RTX 4070

Sampler er_sde

Scheduler beta

Steps 9

CFG Scale 1

Seed 982341

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 (Sick Ollie DiT) Civitai #143363839 Min 10GB VRAM 1216×912 RTX 4070 Verified

Freya Lace Boudoir: Krea 2 Photorealism Recipe

Pixel-exact reproduction of Civitai artwork #143363839 featuring RaymondLuxuryYacht Freya Krea 2 character architecture, Realism Engine v3.1, and Wan 2.1 16-channel VAE decoding.

Blueprint Summary RTX 4070 Verified

Reproducible ComfyUI workflow for Civitai #143363839 Freya Lace Boudoir: Krea 2 Photorealism Recipe using Krea 2 Turbo (Sick Ollie DiT) at 1216×912 resolution. Requires minimum 10GB VRAM with sampler er_sde and scheduler beta (9 steps). Includes 1-click terminal model sync and canvas JSON graph.

Node Graph Pipeline 12 Total Nodes

Verify in Resolver

01 Load Models

UNETLoader

5 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 wires

Model & Asset Setup 1-Click Script

Run in your ComfyUI root:

curl -fsSL https://decomfy.com/api/scripts/civitai-freya-lace-boudoir-krea2.sh | bash

Positive Prompt

rlyfreya, golden brown hair with bangs, A luxury editorial glamour photoshoot of Freya, a stunning woman with long honey brown wavy hair cascading over her shoulder. She wears an elegant designer white lace-trimmed camisole top and matching chic white satin boy-shorts, paired with delicate sheer white thigh-high stockings featuring intricate lace trim. She is reclining gracefully on a plush bed dressed in a blossom floral-patterned blanket with subtle pink and beige tones on clean white fabric. Her gaze is directed toward the camera with calm, magnetic eyes. Soft diffused studio lighting, gentle rim light, warm natural skin tones, shallow depth of field, 8k resolution, crisp professional lookbook photography.

Negative Prompt

blurry, low quality, distorted, extra limbs, ugly, deformed, oversaturated, painting, cartoon, doll, plastic

LoRA Adapter Stack 2 Adapters

RTX 4070 Calibrated Weights

01 RLY-thot_shot-KREA2-freya-v1-trigger-rlyfreya.safetensors +1

02 realism_engine_krea2_v3.1.safetensors +0.9

Required Models 5 Models

Disk Space Required: 19.9 GB (5 models · DiT/Base: 13.5 GB · Text Encoder: 4.4 GB · LoRAs: 1.7 GB · VAE: 254 MB)

models/diffusion_models/ 13.5 GB Civitai

sickOllie_krea2.safetensors Krea 2 Turbo / Sick Ollie quantized DiT diffusion 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/ 218 MB Civitai

RLY-thot_shot-KREA2-freya-v1-trigger-rlyfreya.safetensors Weight: 1.0 (Freya character sculpting adapter & facial likeness)

Get

models/loras/ 1.49 GB Civitai

realism_engine_krea2_v3.1.safetensors Weight: 0.9 (Realism Engine v3.1 photorealistic skin and specular lighting)

Get

Field Notes RTX 4070 Benchmark

Benchmark: 33s on RTX 4070 (10.1 GB VRAM peak)

Ground-Truth Reproduction & White-Weapon Protocol: Reverse-engineered from Civitai #143363839 authored by RaymondLuxuryYacht. Employs the Krea 2 DiT architecture combined with Qwen3-VL 4B text encoder and Wan 2.1 16-channel VAE (preventing inverted contrast artifacts). Chains the RLY Freya character adapter with Realism Engine v3.1. Features pre-wired Dual Prompt conditioning: Node A provides an instant compliant glamour lookbook, while Node B holds the standby raw prompt for 1-click local cable swapping. Benchmarked at 33s on RTX 4070.

Frequently Asked Questions FAQ

What GPU and VRAM are required to run Civitai #143363839 Freya Lace Boudoir: Krea 2 Photorealism Recipe?

This workflow requires a minimum of 10GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at 1216x912 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.