Riot Diffusion XL | League of Legends Splash Art, Arcane, Valorant, Runeterra, Wild Rift, Mobile Legends, Artstation, Pixiv

#リーグ・オブ・レジェンド

無料新規登録で10,000クレジットGET！

新規登録当日にクレジットを付与！

新規登録で画像を8枚無料生成！

新規登録当日にクレジットを付与！

アップロード日時: 2026/01/14 20:29
採用数: 524
レビュー: 普通 (1)
サンプリングステップ: 20
サンプリング方法: Euler a
CFGスケール: 5.5
ネガティブ: low aesthetic, booru, tumblr, ugly, disfigured, old, oldest, text, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, jpeg artifacts, signature, watermark, username, conjoined, ai-generated, error, fewer digits, bad reflection, bad composition, nonsense, artistic error, overrendered, melted, unclear shapes, worst quality, bad quality, very displeasing, displeasing,
権限: 画像生成と共有を許可する
ユーザーによるモデルのダウンロードを許可する
生成画像の商用利用を許可する

詳細説明

Make sure to use "best aesthetic" in the positive prompt

For the type of Riot style you want to go for, choose some of this for a positive prompt:

lolsplashart

arcane

valorant

Finetuned on 100k artworks/images relating to riot games.https://huggingface.co/Totsukawaii/RiotDiffusionPlease 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.UsageMake sure you have at least 12gb vram.Images were captioned with the format: {aesthetic caption if any}, {manual caption}, {WD14 caption}, {llava llama caption} Make sure to use "best aesthetic" in the positive promptNotesAnyone can recreate sample images for free using Amazon SageMaker or Google Colab - Model may be inclined towards anime styled imagery as at least half of the dataset are anime styled images