Civitai #145008974: E-Girl Flash Hardwood Snapshot - BloomGirls & Krea 2 Turbo
Full Resolution
Generation Specs RTX 4070
Sampler euler
Scheduler simple
Steps 10
CFG Scale 1
Seed 145008974
Target VRAM 12GB
VRAM 8GB - 12GB
GPU Compatibility
Optimal Performance

Runs entirely in VRAM with no memory swapping.

Krea 2 Turbo (Official Comfy-Org) Civitai #145008974 Min 8GB VRAM 832×1248 RTX 4070 Verified

E-Girl Flash Hardwood Snapshot - BloomGirls & Krea 2 Turbo

High-angle candid flash snapshot featuring an edgy e-girl sitting on dark polished hardwood, natural skin micro-texture, and dramatic camera flash falloff on Krea 2 Turbo.

Blueprint Summary RTX 4070 Verified

Reproducible ComfyUI workflow for Civitai #145008974: E-Girl Flash Hardwood Snapshot - BloomGirls & Krea 2 Turbo using Krea 2 Turbo (Official Comfy-Org) at 832×1248 resolution. Requires minimum 8GB VRAM with sampler euler and scheduler simple (10 steps). Includes 1-click terminal model sync and canvas JSON graph.

Pipeline Flow 11 Nodes
Open 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
Node Graph 0 nodes
MODEL CLIP LATENT VAE IMAGE

Model & Asset Setup Setup Script

Run in your ComfyUI root:

curl -fsSL https://decomfy.com/api/scripts/civitai-egirl-flash-hardwood-krea2.sh | bash

Positive Prompt

bl00m, high-angle candid flash photo of a stylish 21-year-old e-girl sitting on a dark polished hardwood floor at night, leaning back on her hands, smiling warmly up at the camera. She has long brunette partly braided hair, winged eyeliner, and glossy lips. She wears a fitted black leather cropped biker jacket over a sleek charcoal silk camisole and a pleated dark skirt. Dark room illuminated solely by harsh direct on-camera flash, sharp specular highlights, crisp hard shadows cast against the floor, authentic 35mm amateur snapshot texture, intimate candid realism.

Negative Prompt

unclothed, disrobed, revealing clothes, lowres, blurry, bad anatomy, deformed hands, extra fingers, low quality, artifacts, distorted proportions, text, watermark, cartoon, 3d render, plastic skin
Prompt Customization: This workflow is pre-wired and calibrated. Swap this prompt with your own character, subject, or style without breaking the pipeline.

LoRA Adapter Stack 2 Adapters

RTX 4070 Calibrated Weights
01 BloomGirls UltraRealism LoRA +0.8
02 Famegrid Natural Realism LoRA +0.7

Required Models 5 Models

Required Storage: 19.6 GB (5 models · DiT/Base: 12.6 GB · Text Encoder: 4.9 GB · LoRAs: 1.9 GB · VAE: 253 MB)
models/diffusion_models/ 12.56 GB HuggingFace
krea2_turbo_int8_convrot.safetensors Official Krea 2 Turbo INT8 ConvRot Diffusion Transformer core
models/text_encoders/ 4.88 GB HuggingFace
qwen3vl_4b_fp8_scaled.safetensors Official Qwen3-VL 4B FP8 Scaled Text Encoder (CLIPLoader type: krea2)
models/vae/ 253 MB HuggingFace
qwen_image_vae.safetensors Official 16-channel Video & Image VAE
models/loras/ 447 MB HuggingFace (Mirror)
krea2-bloomgirls-realism-step00004000.safetensors Weight: 0.8, Trigger: 'bl00m' (BloomGirls UltraRealism LoRA for refined facial geometry and delicate makeup rendering)
models/loras/ 1.49 GB HuggingFace (Mirror)
Famegrid-Natural-V1-Krea-2.safetensors Weight: 0.7 (Famegrid Natural Realism LoRA for natural skin pores, high dynamic range, and candid lighting bounce)

Field Notes RTX 4070 Benchmark

Benchmark: Rendered on NVIDIA GeForce RTX 4070 (12GB VRAM, CUDA 12.4)
1. ARCHITECTURAL REASONING & COMPOSITION GEOMETRY: Deconstructs high-angle top-down spatial composition within candid on-camera flash photography. High-angle perspectives typically cause perspective distortion or severe limb foreshortening artifacts in diffusion latents. Chaining BloomGirls UltraRealism (v1.0, trigger bl00m) with Famegrid Natural Realism LoRA stabilizes the face geometry, preventing triangular facial warping while capturing delicate winged eyeliner and micro skin specular reflections. Structured garment anchoring (cropped black leather biker jacket over a silk camisole and pleated skirt) gives clean edge contours against the dark polished hardwood floor, preventing latent collapse without requiring post-hoc inpainting. 2. CABLE ROUTING & SIGNAL TOPOLOGY: Sequential two-stage LoRA injection architecture feeding from Krea 2 Turbo INT8 UNET (krea2_turbo_int8_convrot.safetensors) and Qwen3-VL 4B text encoder (qwen3vl_4b_fp8_scaled.safetensors). The first stage injects BloomGirls (weight 0.8) to establish facial structure and style conditioning; the second stage injects Famegrid (weight 0.7) to inject authentic skin pores and harsh flash shadow gradients. Conditioning flows into a single deterministic positive conditioning node directly connected to KSampler, ensuring 100% WYSIWYG canvas fidelity. Latents decode cleanly through native qwen_image_vae.safetensors. 3. HARDWARE BENCHMARKS & CONSUMER GPU FOOTPRINT: Benchmarked and verified on host NVIDIA GeForce RTX 4070 (12GB VRAM, CUDA 12.4). Peak VRAM usage reached 4.5 GB during the 10-step Euler sampling at 832x1248 resolution. Generation latency completed in 95.7 seconds with zero host RAM offloading, proving full real-time viability on standard 8GB and 12GB consumer graphics cards.

Frequently Asked Questions FAQ

What GPU and VRAM are required to run Civitai #145008974: E-Girl Flash Hardwood Snapshot - BloomGirls & Krea 2 Turbo?

This workflow requires a minimum of 8GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at 832x1248 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 43 workflows
Krea 2 DiT
Fast Turbo / DMD2 #144970991

Steam Lounge Portrait - Dual LoRA & Krea 2 Turbo

10st · euler 832×1248 8GB
Krea 2 DiT
Fast Turbo / DMD2 #144982792

Candid Flash Loft Portrait - SNOFS & Krea 2 Turbo

10st · euler 832×1248 8GB
Krea 2 DiT
Fast Turbo / DMD2 #144950510

Edinburgh Stone Suite - Silk Camisole Candid & Krea 2 Turbo

12st · euler 896×1152 8GB
Action completed