<span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">2000 steps trained lora for IllustriousXL+Trex style 2.5d generations. SFW &amp; NSFW. <span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">Trigger: 2.5d <span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">Run at strength 1.0 for optimal results. The lora works also well anywhere withing 0.7-1.0. Tested on Euler/simple on both Fastvideo H3 and the usual Turbo loras, so you can run it on 6-8 steps no problem. Best results with 20 steps without turbo lora (marginal improvement for those who want maximum quality). I trained this lora also all the way to 4000 steps but that overbaked it so I retracted back to 2k steps which provided a much more consistent result without overcooking the style completely. <span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">The lora is trained for Ref2va<span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">, but works also on first-last-frame. <span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">I wanted to create this lora because Minimax defaults to a pure 2d style (anime) while struggling to maintain this specific style if using ref2va. I got tired of generating first or last frame images so I decided to create a proper style lora. <span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">I will work on creating more flexibility with body parts in the next version of this lora, possibly merging it with some NSFW loras for actions. <span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">Let me know in the comments how the lora worked for you! <span style="background-color:rgb(36, 26, 27);color:rgb(255, 255, 255);font-family:&quot;ABC Oracle Plus Variable&quot;, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, roboto, arial, sans-serif;font-size:16px">-Stuubzzz

Minimax H3 - 2.5d style lora [IL+Trex]

Better movement and camera angles. Doesn't direct towards softcore nudity anymore. Trained on 50 3s clips at 3500 steps.

Files with SHA256: f8f70aeef75512e3721b6375c910b0d0122e89b63394f9167a34172be3ef255b