<p>Finetuned on 100k artworks/images relating to riot games.</p><p><a target="_blank" rel="ugc" href="https://huggingface.co/Totsukawaii/RiotDiffusion">https://huggingface.co/Totsukawaii/RiotDiffusion</a></p><p></p><p>Please do not post AI images generated from this model online. Please use it only for yourself, or only share it within a closed group. Training images were used without consent.</p><h1 id="heading-2479">Usage</h1><ul><li><p>Make sure you have at least 12gb vram.</p></li><li><p>Images were captioned with the format: <span style="color:rgb(219, 222, 225)">{aesthetic caption if any}, {manual caption}, {WD14 caption}, {llava llama caption}</span></p></li><li><p><span style="color:rgb(219, 222, 225)">Make sure to use "best aesthetic" in the positive prompt</span><br /></p></li></ul><h1 id="heading-2479">Notes</h1><ul><li><p>Anyone can recreate sample images for free using Amazon SageMaker or Google Colab - guide in my discord server</p></li></ul><ul><li><p>Model still undertrained</p></li><li><p>Model may be inclined towards anime styled imagery as at least half of the dataset are anime styled images</p></li></ul><p></p><h1 id="heading-2480">Links</h1><p>Join my discord server, for more image samples, dataset tags/captions, free image generation, Q&amp;A/Help, regular updates, and more.</p><p><a target="_blank" rel="ugc" href="https://discord.gg/2RBWXFuVV6">https://discord.gg/2RBWXFuVV6</a></p><h2 id="heading-2481"><br />Credits</h2><p>Stabilty AI - Stable Diffusion XL base model</p><p>Riot Games - majority of the artwork</p><p>Kohya ss sd scripts - trainer</p>

Files with SHA256: 6433d9419d0f8781954a4f823101ca180aaad4f76e80753310425c39697dbf27