<p>Doesn't make images realistic, but enhances the realism of images - it works well with other lora that I've tried so hopefully it's helpful. All examples are raw, unedited outputs.</p><p></p><h3 id="v2.0:"><span style="color:rgb(76, 110, 245)">V2.0:</span></h3><p>Revised dataset - more NSFW - trained much longer. This tends to have a more noticeable impact on color temperature (warmer) and composition compared with other versions, but I also think it's more realistic</p><p></p><h3 id="v1.0:"><span style="color:rgb(76, 110, 245)">V1.0:</span></h3><p>Original realism enhancer that I made that seemed to work reasonably well and maintained consistency with loras.</p><p></p><p>I've continued to experiment and will release some updates - unless there is a meaningfully better model, I'll keep iterating under the V1.0 enumeration.</p><h3 id="alt-1.0:"><span style="color:rgb(76, 110, 245)">ALT 1.0:</span></h3><p>Alternative dataset from V1.0 - not better or worse, but it seemed usable so I figured I'd share it - I think it's close to 2.5D than V1.0</p><h3 id="alt-1.1:"><br /><span style="color:rgb(76, 110, 245)">ALT 1.1:</span></h3><p>Alternative training optimizer with the same dataset as ALT 1.0 - no better or worse</p><p></p>

anima realism enhancer

<p>New dataset - trained much longer. I think this is noticeably better, but the trade-off is that it's less universal/more of a shift of the output compared to no lora.</p>

Files with SHA256: d38f4fab9fcc95f4e0c769b48f61d8dd9ceeaabf131176a6386283307d97092a