<h2 id="this-is-an-experimental-piece.-i-just-wanted-to-test-whether-some-poses-that-defy-normal-human-body-structure-could-be-effectively-trained-into-a-lora-and-the-results-have-been-very-satisfying!-this-motivates-me-to-expand-the-dataseti-only-used-six-33-frame-videos-to-train-it-and-three-of-those-videos-were-generated-by-me-using-wan2.1-vace.-this-was-challenging-because-dwpose-couldn't-recognize-these-unusual-movements!">This is an experimental piece. I just wanted to test whether some poses that defy normal human body structure could be effectively trained into a Lora, and the results have been very satisfying! This motivates me to expand the dataset<br />I only used six 33-frame videos to train it, and three of those videos were generated by me using wan2.1 vace. This was challenging because DWpose couldn't recognize these unusual movements!</h2><p></p><h2 id="i-only-tried-testing-it-with-some-simple-prompts-you-can-try-using-complex-prompts-and-hopefully-it-will-perform-well-too.tested-at-480x848-and-720x1280-resolutions-not-sure-how-it-performs-at-other-resolutions.">I only tried testing it with some simple prompts; you can try using complex prompts and hopefully it will perform well too.<br /><br />Tested at <span style="color:rgb(250, 82, 82)">480x848 </span>and <span style="color:rgb(250, 82, 82)">720x1280</span> resolutions, not sure how it performs at other resolutions.</h2><pre><code>The girl is wearing a blue bikini and black high heels, 
showcasing the "sanzhe" pose on a dimly lit stage, 
holding the tips of her shoes with both hands, her face showing pain</code></pre><h2 id="i've-only-tested-it-using-wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors-with-4-step-sampling">I've only tested it using <span style="color:rgb(250, 82, 82)">wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors with 4-step sampling</span></h2><h2 id="i-don't-know-how-this-lora-performs-without-acceleration.">I don't know how this Lora performs without acceleration.</h2><p></p>

Files with SHA256: 589c6138e577e609b58d15d9da5a992d1ffe1412dd6389c9e191d5baacc6a5c1