Edit: added a version trained on Animagine v3.1I have no idea how to prompt with Animagine, so sample prompts are pluck from Animagine samples.My attempt at creating a tachi-e lora for PonyXL checkpoints (basically a full body character drawing on white or transparent background) . Version 0.2 are retrained with more "faux figurine" images.Trigger:<pre><code>tachi-e, full body, simple background, white background</code></pre>Might best be "primed" by using seed images and 0.85~0.95 denoise.Below are some I usually use.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/40e88117-55c7-4387-aece-36f7ad48b4b6/width=525/40e88117-55c7-4387-aece-36f7ad48b4b6.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1d13eb5e-7142-4181-8ea5-0ee756fb08f3/width=525/1d13eb5e-7142-4181-8ea5-0ee756fb08f3.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c4a297b5-82db-4178-ac57-262b94772025/width=525/c4a297b5-82db-4178-ac57-262b94772025.jpeg" />

ponytachi

Retrained with more faux figurine images, should allow environment elements more easily.

Files with SHA256: 933e09710bf2487f157ecf47f8e176f109c38640622bb8678ed55f2e0f57181f