Took 53 cleaned images prepared for WAI-IL and trained a WAI-Anima character LoRA with AnimaLoraToolkit + RunPod. Training itself ran for $1.22, but at inference the side ponytail direction wouldn't shift with Danbooru tags or natural language. Verification record showing the issue is a directional bias inherited from Anima base (preview3-base onward).
Testing WAI-Anima v1 on an RTX 4060 Laptop GPU (8GB VRAM). Ran into a tqdm OSError nightmare trying headless execution via ComfyUI API, but once launched normally it generates in 55 seconds.
WAI0731 (creator of WAI-Illustrious) released WAI-Anima v1, a derivative model based on Anima. In the two months since the February Anima article, derivative models have surged along with a LoRA toolkit and text encoder upgrades. Hands-on comparison of preview3-base and WAI-Anima v1.