<h2 id="ltx-2.3-v2.5-update">LTX 2.3 V2.5 UPDATE</h2>I have trained with a bit more variety, to get a more stable effect.Hope you like it, let me know in the comments :)Also check my updated base workflow with the new Ltx 2.3 1.1 distill lora<a target="_blank" rel="ugc" href="https://civarchive.com/models/1598638?modelVersionId=2864162">https://civarchive.com/models/1598638?modelVersionId=2864162</a><h2 id="ltx-2.3-update">LTX 2.3 UPDATE</h2>Yes made my first attempt on training a LTX lora. It clearly adds some nice bounce, but im not sure if its there yet. Let me know in the commentsIn doubt use my base workflow:<a target="_blank" rel="ugc" href="https://civarchive.com/models/1598638?modelVersionId=2831320">https://civarchive.com/models/1598638?modelVersionId=2831320</a><h2 id="wan">WAN</h2>This lora is for animating bouncing breasts with Wan. Since I felt there was a lack of it here ;)Used I2V-14B-720P as base.Since ppl were asking about my training worklfow: I have used 7 videos with about 4 second length, with faces cut off. I have described what happens e.g. A girl with blonde extensions is standing in a hotel room, she wears black lingerie, her breasts are bouncing shaking or wobbeling up and down, her hands stand still, her face is cut off Then I used Musubi-Tuner with default parameters and trained about 32 epochs, with my 4090 it was done in about 35 min. That's all :)

Bouncing Boobs - LTX / Wan

bounceV_01.safetensors

Bouncing Boobs - Wan I2V 14B

bounceV_01_I2V_720p

LTX 2.3 V2.5

LTX 2.3 V2

WAN 2_2 Bounce Low

WAN 2_2 Bounce High

bounceV_01_I2V_480p

bounceV_01_T2V

<h3 id="luna-belle-the-soft-natural-beauty-zw6k6gc37">Luna Belle – The Soft Natural Beauty</h3><ul><li>Style: Simple and sexy — black crop top, high-waisted skirt</li><li>Face: Symmetrical with warm brown eyes, full lips, wide smile</li><li>Hair: Long chestnut hair, soft waves</li><li>Body: Hourglass figure, curvy but natural</li><li>Tattoos: Few, small and cute (like floral or minimal designs)</li><li>Vibe: Friendly, confident, sweet yet alluring</li></ul>

Luna

luna_.safetensors

Works also well with the 480p model

Tried to train with T2V model. But the results with the I2V base model were just better so ill upload this version, since it just works pretty good

Files with SHA256: bddb45b506f91c4691e23282da48f3684e2b935df90e642ef1108616ff4fdfb1