Thank you for joining the auction, and I really appreciate your support in keeping on-site generation going!<a target="_blank" rel="ugc" href="https://civarchive.com/articles/19075/at-that-moment-i-was-not-alone">https://civarchive.com/articles/19075/at-that-moment-i-was-not-alone</a><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">v3_anime -Up to now, my checkpoints have been gradually moving toward realism. <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">This new release marks a shift back toward an anime-inspired aesthetic — a deliberate return to my creative roots, shaped by my current style and the LoRAs I’ve developed.<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">v2.0 - I aimed for more realism this time, trying to capture that fine balance between illustration and photorealism. Some people might still prefer v1.1, but I wanted to share this new direction. Please experiment with prompts and LoRA combinations to find your own sweet spot.v1.1 – Tweaked for a slightly more realistic look. Feel free to switch between v1.0 and v1.1 depending on your preference.v1.0– This version is merged by <a target="_blank" rel="ugc" href="https://civarchive.com/models/687637/speciosa-anime">Speciosa Anime</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/693017/pony-mix-dream">Pony-Mix-Dream</a>.VAE: Built-in

Dreamisoa_remix - v2.0_SemiReal

Changes from v1.1: I aimed for more realism this time, trying to capture that fine balance between illustration and photorealism. Some people might still prefer v1.1, but I wanted to share this new direction. Please experiment with prompts and LoRA combinations to find your own sweet spot. For reference, I’ve been testing locally on an M1 Mac.

Files with SHA256: a466ef9a0ae3e5c2070416d69a4c9427c13a0b77e845c740ed6df3b8d5ee899d