Lora of the cartoon <a target="_blank" rel="ugc" href="https://www.imdb.com/title/tt0283226/">Totally Spies</a> (season 1 from 2001). It's a style Lora, and it is not trained on the characters, so no specific trigger tokens for the girls.<h3 id="qwen">Qwen</h3>2512It was trained on 2512, but I prefer to use the original Qwen-Image model for inference.Showcase images :<ul><li>Original Qwen-Image (BF16)</li><li>Lightning lora (4 steps)</li><li>5 steps / 1 CFG</li><li>DDIM &amp; Beta</li><li>Lora strength 1</li></ul><h3 id="klein-9b">Klein 9B</h3>v1Showcase images :<ul><li>Distilled model </li><li>768x1152</li><li>Euler / normal / 4 steps / CFG 1</li><li>Hires steps : 4 / NMKD_SIAX @0.35 / x2</li><li>Lora strength of 0.8-1</li></ul><h3 id="flux">Flux</h3>With a weight of 0.8, I start my prompt with : 'a cartoon style image of'

Totally Spies style

totally_spies_style_v1.safetensors

Files with SHA256: 1d514ef7c2dfc9111ba0d022d9524ded25040ee4f4e14de69dc21d2192e9d85d