<h2 id="description">📋 Description</h2>A merge based on KREA2 Turbo, optimized for fast and high-quality generation. This model combines the strengths of the KREA2 architecture with custom tuning for improved results across various styles.<hr /><h2 id="recommended-generation-settings">⚙️ Recommended Generation Settings</h2>ParameterValueSteps8SamplerEuler aSchedule typeBong TangentCFG scale1Seed3448636919Resolution1536×2048Modelfascium_SFWKREA2_fp8Model hash98d064dc8fModule 1qwen_image_vaeModule 2qwen3vl_4b_fp8_scaledDiffusion in Low BitsAutomatic (fp16 LoRA)RNGCPUStyle SelectorEnabled (Style: <code>base</code>)Krea2 Enhancer✅ Enabled<hr /><h2 id="tips-and-notes">💡 Tips &amp; Notes</h2><ul><li>Low CFG (1.0) — This model is designed to work best with a very low CFG scale. Higher values may cause artifacts or oversaturation.</li><li>Few steps needed — Only 8 steps are required thanks to the Turbo architecture. Going higher won't improve quality and will just waste time.</li><li>Krea2 Enhancer — Make sure to enable the Krea2 Enhancer for best results.</li><li>Style Selector — Set to <code>base</code> by default. You can experiment with other styles, but disable randomization for consistent output.</li><li>Resolution — Tested at 1536×2048 (portrait). The model supports various aspect ratios, but keep total pixel count around ~3MP for optimal performance.</li><li>fp8 quantized — This is an fp8 version for reduced VRAM usage while maintaining quality.</li></ul><hr /><h2 id="trigger-words-prompt-guide">🖼️ Trigger Words / Prompt Guide</h2>No specific trigger words required. Write natural, descriptive prompts. The model responds well to detailed style and composition descriptions.<hr /><h2 id="known-limitations">⚠️ Known Limitations</h2><ul><li>SFW-focused merge</li><li>Best results with the exact settings above — deviating from recommended CFG/sampler may degrade output quality</li></ul><hr />Feel free to adjust the model name, add your own example images section, or tweak any details to better match your vision! 🎨

FASCIUM KREA2

FMP1610-int8_convrot.safetensors

FMP1610-int4_convrot.safetensors

FMP1610-nvfp4.safetensors

MASTERPIECE EDITION 4

SOFT vers2

SOFT

MASTERPIECE EDITION 5

MASTERPIECE EDITION 3

MP2. SURREALISTIC

MASTERPIECE EDITION

REALISTIC MERGE NSFW

REALISTIC MERGE SFW

EXP01092026

EXPERIMENTAL2008

NSFWMERGE4

SAFEMERGE4

NSFW3_MERGE

EXPERIMENTAL_NSFW3007

SAFE2 MERGE

NSFW2_MERGE

BASE2 MERGE

EXPERIMENTAL_NSFW

SAFE MERGE

NSFW MERGE

BASE MERGE

EXPERIMENTAL7 NSFW

EXPERIMENTAL

v2.0

v1.0

Files with SHA256: be143df351c558b44615ed9731baddb89edc817960adaf8b9892bb93588a01f4