This LoRA makes images of people who look like they're in a wind tunnel. I wanted this for some reason, so here it is lol.Trigger is w1nd8l0wn photo, but it helps to add things like closeup, windy, and/or wide open mouth and flapping cheeks.NOTE: The Z-Image Turbo version doesn't seem to play nice with character LoRAs. It can distort the likeness and introduce errors/deformations in the scene. Try using more (e.g., 18) steps and increasing the model shift (e.g., 10). Also, for less noisy/blotchy images use the <a target="_blank" rel="ugc" href="https://github.com/erosDiffusion/ComfyUI-EulerDiscreteScheduler">FlowMatch Euler Discrete Scheduler</a> along with Euler_ancestral.If you can't get a closeup photo, make sure you aren't describing things like pants, shoes, excessive background details, etc.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7b3f4aa2-87e4-4cfb-9879-044edb1a971b/width=525/7b3f4aa2-87e4-4cfb-9879-044edb1a971b.jpeg" />

Files with SHA256: bf60ce8d36b57b75ada71112c1f017d21ccd8e68c15ec341292d5fa8bac54b04