Introducing the LTX 2.3 version of my other <a rel="ugc" href="https://civarchive.com/models/2223955/breast-expansion-wan">Breast Expansion LoRA</a>. This model was trained on clothed video clips only and it works well in both Image-to-Video and Text-to-Video scenarios. Use a strength of 1.0 in either case.Important:<span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);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"> As always with my models, this LoRA does not represent any real person in any way. If this model produces a video with any resemblance at all to a real person, that is purely an accident of AI random generation.The keyword in the LoRA is "brstgrw" and you can further guide some of the results with descriptive prompting.My samples are a mix of I2V and T2V and are labeled so you'll know which is which. I used a variety of different schedulers (Euler, Euler Ancestral CFG++, LCM, etc.) and the model performs well with all of them. I often use my <a rel="ugc" href="https://civarchive.com/models/2736657/bustywomen-ltx">Busty Women LTX LoRA</a> at low strength (0.10 - 0.20) in addition to help with natural movements.I hope you all enjoy making video clips with this model and I can't wait to see what creative movies you all can come up with.

Files with SHA256: 3c191445432d3181ea78225cdfa936e8b81d9d2bddbd2d99b3f8c30839b6e941