<h3 id="concept">Concept</h3><p></p><p>This was an experiment to see what I could get WAN to do with very little input, the results came out decent so I thought I'd share. I wanted to dress a character in a specific outfit from VAM (Noc_this maid outfit) and was really struggling to get WAN to understand my prompt. So I booted up VAM, took 17 screenshots of a character with the outfit on from various angles and different boob sizes, auto-captioned them using Joycaption, punted it all into diffusion pipe and a few hours later got a working model. The results are reasonably accurate so decided to share, so everyone can have their own big tiddy goth maid.</p><p></p><h3 id="usage">Usage</h3><p></p><p>Should work in both T2V and I2V. Prompt is simply:</p><p>Base prompt T2V is:</p><pre><code>A woman wearing a exposed maid outfit. She wears a black, long-sleeved leotard with a high neckline and a white maid apron that exposes her breasts.The apron has a frilled edge and ties at the back. The leotard is very high-waisted. </code></pre><p>For I2V assuming you're using the outfit change lora:</p><pre><code>The woman has a sudden outfit change into an exposed maid outfit. She wears a black, long-sleeved leotard with a high neckline and a white maid apron that exposes her breasts.The apron has a frilled edge and ties at the back. The leotard is very high-waisted. </code></pre><p>Thats it, enjoy.</p><p></p><h3 id="training">Training</h3><p></p><p>As mentioned, 17 images with 2 repeats trained at 0.6mp on high and 1mp on low. Batch 14 and 8 respectively. Only trained it for 25 epochs on both low and high. LR was quite high as I was impatient at 3e-4. Trained on diffusion pipe on 4x3090s</p><p></p>

Files with SHA256: 57791559ba74d570cfe5c819cf0cb155c18ddc7092768503d38d8e8384a22fd1