Update: - V3 is about half RAW still runs at 8-12 steps. - Added V3 FP8. - Added V3 Int4 ConvRot SR (stochastic rounding). ⚠️ IMPORTANT — Applies to v1.0, v1.1,v2, v3 ⚠️ ❌ Do NOT use the INT8 Fast custom node. This checkpoint is already in native ComfyUI INT8 (ConvRot) format. ✅ Use the standard ComfyUI Load Diffusion Model node.Requirements - ComfyUI v0.27+ - ComfyUI KitchenKrea2 Center v1: similar, experimenting with some block merging.Krea2 Center v0.5 explores whether Krea2 can become more expressive through carefully balanced LoRA merging while preserving the model's realism, flexibility, and overall character. The goal isn't to replace Krea, but to gently extend its emotional range across portraits, fantasy, sci-fi, and stylized scenes.Added Int8: about 25% faster on 50 series Nvidia don't have a 40 or 30 series to test.<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit <a target="_blank" rel="ugc" href="https://krea.ai/krea-2-licensing">https://krea.ai/krea-2-licensing</a><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">.

Krea2_Center

bf16 is the nvfp4 quant ;)nf4=int4 convrot

krea2Center_v404bitNvfp4Int4.safetensors

v4.0 4bit (nvfp4 / int4)

v 4.0 8bit (fp8,int8)

v3.0 INT8 ConvRot Learned

v3.0 Int4 ConvRot SR

v3.0 Int8 ConvRot / fp8

v2.0 int4 convrot

v2.0 int8 convrot and fp8

v1.1 int8 convrot

v1.0 int8 convrot

v0.5 Int8

v0.5 fp8 and nvfp4

Files with SHA256: 5148271dd304836c2b6eb3fbf7abce88e592381e0aed98ab76aa46d4b3f1290b