[SD 2.1][TextualInversion]CharTurner - Character Turnaround helper for 1.5 AND 2.1! CharTurner V2 - For 2.1
<h1>CharTurner</h1><p>Edit: <strong>controlNet</strong> works <strong>great </strong>with this. Charturner keeps the outfit consistent, controlNet openPose keeps the turns under control. </p><p><strong>Three versions,</strong> scroll down to pick the right one for you.</p><p>If you're unsure of what version you are running, it's <em>probably</em> 1.5, as it is more popular, but 2.1 is newer and gaining ground fast.</p><p><strong>Version 2, for 2.0 and 2.1 models<br />Version 2, for 1.5 models<br />Version 1, for 1.5 models</strong></p><p>BONUS: <a target="_blank" rel="ugc" href="https://civitai.com/models/7252/charturnerbeta-lora-experimental">Experimental </a>LORA released<br />used at your own risk. :D (mixes well tho)</p><p>Hey there! I'm a working artist, and I loathe doing character turnarounds, I find it the least fun part of character design. I've been working on an embedding that helps with this process, and, though it's not where I want it to be, I was encouraged to release it under the <a target="_blank" rel="ugc" href="https://en.wikipedia.org/wiki/Minimum_viable_product"><u>MVP</u></a> principle.</p><p>I'm also working on a few more character embeddings, including a head turn around and an expression sheet. They're still way too raw to release tho.</p><p>Is there some type of embedding that would be useful for you? Let me know, i'm having fun making tools to fix all the stuff I hate doing by hand.</p><p>v1 is still a little bit... fiddly.</p><ul><li><p>Sampler: I use DPM++ 2m Karras or DDIM most often.</p></li><li><p>Highres. fix ON for best results</p></li><li><p>landscape orientation will get you more 'turns'; square images tend toward just front and back.</p></li><li><p>I like <a target="_blank" rel="ugc" href="https://civitai.com/models/2540/elldreths-stolendreams-mix"><u>https://civitai.com/models/2540/elldreths-stolendreams-mix</u></a> to make characters in.</p></li><li><p>I use an embedding trained on my own art (smoose) that I will release if people want it? But it's an aesthetic thing, just my own vibe.</p></li><li><p>I didn't really test this in any of the waifu/NAI type models, as I don't usually use them. Looks like it works but it probably has its own special dance.</p></li></ul><p>Things I'm working on for v2: EDIT: <strong>V2 out, see below! (also v2 2.1)</strong></p><ul><li><p>It fights you on style sometimes. I'm adding more various types of art styles to the dataset to combat this. -<strong> V2 has much better styles</strong></p></li><li><p>Open front coats and such tend to be open 'back' on the back view. Adding more types of clothing to the dataset to combat this. - <strong>Still has this problem</strong></p></li><li><p>Tends toward white and 'fit' characters, which isn't useful. Adding more diversity in body and skin tone to the dataset to combat this. - <strong>v2 Much more body and racial diversity added to the set, easier to get different results.</strong></p></li></ul><p>Helps create multiple full body views of a character. The intention is to get at least a front and back, and ideally, a front, 3/4, profile, 1/4 and back versions, in the same outfit.</p><p></p>
页:
[1]