<p>A detailer model that aims at adding diversity to the generated images.</p><h1 id="recommended-weight-of-~0.75-a174adrw8"><span style="color:rgb(130, 201, 30)">Recommended weight of ~0.75</span></h1><p>I'll continue the work with the model and the dataset.</p><ul><li><p>It's definitely overtuned with too many images of women currently.</p></li></ul><p></p><h3 id="training-notes-xdnnra612">Training Notes</h3><p>The model is trained with very long and complex image captions. The intent was to see if by training with very detailed descriptions, I could increase the prompt understanding.</p><p>I feel like this was not fully achieved with this version of the model. But check out <a target="_blank" rel="ugc" href="https://civarchive.com/models/477442">dAIversity - Prompt Understanding Enhancer - XL Realistic</a> for a more successful version of this.</p>

dAIversity Detailer 1.5 (photo/semi-realistic)

dAIversityLoRA15-PhotoSemiReal.safetensors

v1.0

<p>A detailer model that aims at adding diversity to the generated images.</p><h1 id="recommended-weight-of-~0.75-a174adrw8"><span style="color:rgb(130, 201, 30)">Recommended weight of ~0.75</span></h1><p>I'll continue the work with the model and the dataset.</p><ul><li><p>It's definitely overtuned with too many images of women currently.</p></li></ul><p></p><h3 id="training-notes-xdnnra612">Training Notes</h3><p>The model is trained with very long and complex image captions. The intent was to see if by training with very detailed descriptions, I could increase the prompt understanding.</p><p>I feel like this was not fully achieved with this version of the model. But check out <a target="_blank" rel="ugc" href="https://civitai.com/models/477442">dAIversity - Prompt Understanding Enhancer - XL Realistic</a> for a more successful version of this.</p>

Files with SHA256: ad098c93c5273863297d0a6fe9e435d2f1f1dff33c5103574ec47f2bddad1186