<h3 id="what's-different-about-version-2.0-o6d6ssh1q">What's different about version 2.0?</h3><pre><code>After over a month of more than 10 attempts, I finally chose to train with DoRA, aiming to minimize its impact on limb positioning while handling larger datasets. Just when my patience was about to run out, I was pleasantly surprised by the results.</code></pre><pre><code>I welcome everyone to test it out and share their feedback. I also apologize for not being able to keep up with your comments during this time.</code></pre>==============================<s>This LoRA (Low-Rank Adaptation) is experimental, aimed at exploring the feasibility of training LoRA with Flux.</s><s>The LoRA can make the default female appearance in Flux lean more towards an Asian look. However, it has not undergone any facial beautification or "internet celebrity face" training.</s><s>Usage:</s><s>It is recommended to use weights between 0.4 and 0.65. The latest version of ComfyUI now supports loading Flux LoRA.</s><s>Regarding Training:</s><s>The training was done using the SimpleTuner script with 2,900 images, taking approximately 20 hours.</s><s>Disadvantages/Issues:</s><s>There might be slight impacts on the limbs, with a minor decline in the overall performance of the model. More training or other methods may be needed.</s><s>It is challenging to fit, and the images may easily collapse during learning.</s><s>Testing:</s><s>The following are images generated by ComfyUI Flux1.dev-fp8, 25 steps, with prompts and seeds shown on the images:</s>

Files with SHA256: 3c31291cf5d7f01d12cb5d66093c58b3356e15313926515464a3d89cfbd7499a