Worldly XL | Anime Scenery Lora - v1.0
ハイライトされた画像
推奨プロンプト
score_9,score_8_up,score_7_up,score_6_up,source_anime,<lora:Worldly_XL:1> [your prompt]
score_9, score_8_up, score_7_up, score_6_up, source_anime, <lora:Worldly_XL:1>, solo, 1girl
推奨ネガティブプロンプト
mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background
mosaic censoring, bar censor, censored, source_cartoon, source_pony, source_furry, simple background, lipstick
推奨パラメータ
samplers
steps
cfg
clip skip
resolution
other models
推奨ハイレゾパラメータ
denoising strength
ヒント
Use the extension [sd-webui-color-enhance] set to 0.5 to increase saturation.
Try both Worldly_XL and CoMix BGXL to determine which background enhancement you prefer.
Recommend pairing Worldly_XL with the AutismMix model for best results.
Upscaling method can be followed via the provided link to increase image quality.
クリエイタースポンサー
This lora was trained on roughly 60 images selected for their vibrant and detailed scenery. My goal was to create a lora that could be used in conjunction with character loras to enhance their backgrounds. What this lora does best is cities, nature, beaches and specific details such as random items in a scene. Most of the example images are the lora alone, a few of them used my other lora MeMaxXL to showcase how it enhances the background. More than anything, this lora increases the dynamic range of color compared to base Pony/AutismMix.
If you compare it to my other scenery lora, CoMix BGXL the details and colors are much more prominent and defined. You can try them both and determine which you like best.
To get the results you see in the images above, these are the settings I used.
Prompt(at the start): score_9,score_8_up,score_7_up,score_6_up,source_anime, <lora:Worldly_XL:1> [your prompt]
Negatives: mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,
Sample: DPM++ 2S a
Steps: 26 (Whatever gives you the best results)
CFG Scale: 7
Extension: [sd-webui-color-enhance] set to 0.5 (this increases the saturation a bit)
Upscaling: Follow this method
This lora was trained on AutismMix and I exclusively use AutismMix. I recommend you do the same. All of the examples were made with that model.
