<h2 id="flux-monte-carlo">FLUX Monte Carlo</h2><pre><code>

Note: This model has undergone deterministic bias correction + stochastic regularization. 



Even this took around 2GW of power.



To train a FLUX at FP32 it would take a supercomputer and power-plant.</code></pre><ul><li>This model has 1 Trillion Iterations to restore FP32 precision.</li><li>Do to the complexity of the tensor shape this was done at 10,000 steps per element, with noise guidance based on the tensor.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/1684593?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp32">FP32 T5</a> &amp; <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/1172273?type=Model&amp;format=SafeTensor&amp;size=pruned&amp;fp=fp32">FP32 CLIP</a></li></ul><hr />

Files with SHA256: d25532836eda545622d67e740ed21f5f4d77b78ac919f0a3c15cbb82b998f053