<h3 id="how-to-use">How to Use</h3>This is a style LoRA, designed to be the base layer of your LoRA stack. It creates the foundational aesthetic of realism, upon which you can add character or concept LoRAs.Note: The included ZIP archive contains both the high-noise and low-noise LoRA variants, along with our recommended ComfyUI workflows.<ul><li>Trigger Word: <code>Instacam</code></li><li>Recommended Strength: <code>1.0</code>. Start here and adjust in small increments.</li></ul>I would also like to thank Danrisi, who originally taught us how to train LoRAs and helped make our work possible.

Instagirl WAN 2.2

Even better "amateur" look. More low quality images added to the dataset and I took out all the ones with excessive makup, face shinyness. Fully tested and working with character LoRAs, examples shown here. Alot of the images shown here have a weird dimple thing, but it's more from our character LoRA and not the base LoRA.

Files with SHA256: 9cb7dedda1bc2b68a73da452d15a2fda6c3d674168853daf0408b341ee819d96