<h3 id="klein-9b">Klein 9B</h3>Showcase images :<ul><li>Distilled model</li><li>768x1152</li><li>Euler / normal / 4 steps / CFG 1</li><li>Lora strength of 0.8-1</li></ul><h3 id="qwen:">Qwen:</h3>v2: Retrained on a completely new and higher quality dataset (same one used for training the ZIT version)<h3 id="zit:">ZIT:</h3>Showcase images settings :<ul><li>Lora strength 0.7 - 0.8</li><li>DDIM &amp; Beta</li><li>10 steps &amp; 1 CFG</li><li>1056x1584</li><li>'comic style image'</li><li>Long Markdown type prompt for some of them</li></ul><h3 id="flux:">Flux:</h3>Trained on 30 images handpicked from the comic <a target="_blank" rel="ugc" href="https://en.wikipedia.org/wiki/The_Adventures_of_Tintin">The adventures of Tintin</a> It's a style Lora, so it doesnt really know the characters (except maybe Tintin and his dog which Flux already knew a bit). a bande dessinée style image of with a weight around 0.8-1. (for Qwen it's 1)

Tintin comic style

tintin_style_zit.safetensors

Files with SHA256: 2a8f62c2b6ca0318ea2b0c56bc9c952d4aa5630e8118c0f0dc54ea9569c5ec09