<h3 id="comfyui-native-int8-convrot-fix-(no-more-keyerror:-'int8_rowwise')">ComfyUI Native INT8 ConvRot Fix (No more KeyError: 'int8_rowwise')</h3>If you tried using several INT8 ConvRot versions of this model available on others platforms in ComfyUI (v0.27.0+), you probably encountered a nasty crash: <code>KeyError: 'int8_rowwise'</code>.Why did that happen? Early experimental quantization scripts generated files using row-wise scaling. However, ComfyUI's native INT8 implementation only supports tensor-wise scaling out of the box (<code>int8_tensorwise</code>). Even custom loaders like <code>KJNodes</code> bridge back to Comfy's native core, causing an instant pipeline crash.What this version fixes: I re-quantized the official BF16 model from scratch using the official parameters, strictly forcing <code>--scaling_mode tensor</code>.How to use it:<ol><li>Drop this <code>.safetensors</code> file into your <code>ComfyUI/models/diffusion_models/</code>folder.</li><li>Load it natively using the standard Load Diffusion Model.</li><li>No custom nodes required! Enjoy massive VRAM savings and FP16-like image quality natively on your GPU. </li></ol>Works with Sage Attention too for more speed!

Files with SHA256: 0dbeb82759b7c7cde0d1c56eff6dc4936758254c3297df83df29192dec289709