This lora was trained on about 50-53 images from the games series of Dragon Crown, Odin Sphere and a few other Vanillaware games. The goal of this lora was to capture the style. It's not prefect but it came out pretty damn close. I am satisfied.V4: Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/2458426/anima">Anima 1.0</a>.V3: Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">Noob 1.0 V-Pred</a>.V2: Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/852957/zootlustrious-aesthetic-illustrious-xl-refinement">Zootlustrious.</a>To get the results you see in the images above, <a target="_blank" rel="ugc" href="https://civarchive.com/articles/11427/my-current-sdxl-settings">these are the settings I used.</a>

Vanillaware Style | Anima/SDXL

This version was trained using 53 images on <a target="_blank" rel="ugc" href="https://civitai.red/models/2458426/anima">Anima 1.0</a>, at a resolution up to 1792. So you can comfortably generate around 1792x1792.I had to redo the entire dataset because the XL images were rather poor. So this version uses images from most of Vanilaware's IP. Mainly Dragon's Crown, Odin Sphere, and a variety of the early and more recent work. This style was captured incredibly well.I went through and tagged most of the characters by name but you shouldn't expect to get 1 to 1 replication as that wasn't my intent.

Files with SHA256: 4aa6ef1d9b099b003516b9749145344ea5bc3ea4943e16ddc4594a18145e177d