Civitai #144556340 Inari Fox Shrine: Torii Twilight & Dynamic Cel Shading

Full Resolution

Generation Specs RTX 4070

Sampler

Scheduler

Steps

CFG Scale

Seed Random

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 Checkpoints (Krea2) Civitai #144556340 Min 8GB VRAM × RTX 4070 Verified

Inari Fox Shrine: Torii Twilight & Dynamic Cel Shading

Japanese anime illustration featuring bold brushwork, deep red Torii gates, stone stairs, and an enigmatic white fox with glowing red eyes under illuminated lanterns.

Blueprint Summary RTX 4070 Verified

Reproducible ComfyUI workflow for Civitai #144556340 Inari Fox Shrine: Torii Twilight & Dynamic Cel Shading using Krea 2 Turbo Official Comfy-Org Checkpoints (Krea2) at × resolution. Requires minimum 8GB VRAM with sampler and scheduler ( steps). Includes 1-click terminal model sync and canvas JSON graph.

Node Graph Pipeline 12 Total Nodes

Verify in Resolver

01 Load Models

UNETLoader

6 loaders (DiT, CLIP, VAE)

02 Adapters

LoraLoader

3 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-inari-fox-shrine-krea2.sh | bash

Positive Prompt

japanese anime illustration, painting featuring bold and powerful brushwork, Rich, deep colors.\nFront view,\ntorii gate, long stone steps, from below,\nfantastic, mysterious, lanterns, foreshortening,\nA white fox turns around, red eyes, looking at viewer,\ncolorful, light particles, depth of field, blurred periphery,\nhigh contrast, cel shading, Dynamic shading, \n<lora:refusal_reduction_v2_full_rank:1>\n<lora:training_8553883-20261001003544162-hppu:1> \n <lora:Colorful Burst - Krea2:0.8> BurstDaal

Negative Prompt

worst quality, low quality, score_1, score_2, score_3, bad anatomy, bad hands, watermark, artist name, censor

LoRA Adapter Stack 3 Adapters

RTX 4070 Calibrated Weights

01 Nippon +1

02 Colorful Burst - Krea2 +0.8

03 Krea2 TextFusion Refusal-Reduction LoRA (Updated) +1

Required Models 0 Models

Disk Space Required: 0 MB (0 models · No external weights required)

Field Notes RTX 4070 Benchmark

Benchmark: RTX 4070 (12GB): 1.6s per 8-step generation at 672x1176 via INT8 ConvRot optimization.

Reverse-engineered from the #1 trending showcase on Civitai (324+ reactions). Synthesizes Krea 2 Turbo Int8 diffusion with Qwen3-VL 4B text encoder and dual aesthetic LoRAs (Nippon for ukiyo-e woodblock lines + Colorful Burst for particle bloom) unconstrained via Refusal Reduction v2.

Frequently Asked Questions FAQ

What GPU and VRAM are required to run Civitai #144556340 Inari Fox Shrine: Torii Twilight & Dynamic Cel Shading?

This workflow requires a minimum of 8GB VRAM (recommended 12GB VRAM). Tested and verified on NVIDIA GeForce RTX 4070 (12GB VRAM) at undefinedxundefined 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.