What we have here: The Loras here are trained on ~60-240 MidJourney Images that use my "Personalised Style" + Some other styles. Created this collection for easer use with the onsite generator. The models:ArsMJStyleXL - The base of the Personal Style without other influences. Second version of this base and the Loras Based on it can be found here:<a target="_blank" rel="ugc" href="https://civarchive.com/models/621570/arsmjstyle-sdxl">https://civarchive.com/models/621570/arsmjstyle-sdxl</a>ArsMJStyleXL Light - Almost the same as above, but with much weaker effect.ArtNoveau - Cover was created by @ManukaWatercolor - Cover was created by @Manuka Stained Glass - Cover by @Manuka and @NineeightMosaic - Works great with Stained Glass Lora.New additions:Pixel Art - Plays really well with almost all Loras.Cute - Childbook look and feel lora.Anime - A blend between many Anime styles and my personal Style. A and B are similar, but B is much sharper. Main theme of C is Edo period.CyberPunkYou can find Pony versions in the Model Cards dedicated to the Style with the same name. I also try to add SD 1.5 versions, but some are missing (for now).

ArsMJStyles - SDXL (Style Collection)

The Lora is trained on MidJourney Images that use my "Personalised Style" + Pixel Art.Works without the trigger words ArsMJStylePony, Pixel Art, manyP, fewP IMPORTANT: All 8bit samples in the dataset are tagged with fewP . You can add it to the negative/positive depending on whether you prefer that type of Pixel Art . All "higher quality" 16bit+ samples are tagged with manyPTry lowering CFG if everything is too "melty"Will start adding visible effects at 0.35+ Works great in the 0.4 - 0.8 range, depending on your preference and Lora MixI recommend 1+ for best "Pixel Art" results, if you are not going to mix it with other Loras.

ArsMJStyleSDXL_-_Pixel_Art.safetensors

Pixel Art

Anime B

Anime A

CyberPunk

Anime C

Cute Childbook

Mosaic

Stained Glass

Watercolor

Art Nouveau

ArsMJStyleXL - Lightest

ArsMJStyleXL

The Lora is trained on MidJourney Images that use my "Personalised Style" + Pixel ArtWorks without the trigger words ArsMJStylePony, Pixel Art, manyP, fewP You can find v2 of this model here: <a target="_blank" rel="ugc" href="https://civarchive.com/models/629354?modelVersionId=703625">https://civarchive.com/models/629354?modelVersionId=703625</a> v2 have different color structure and the tagging described below works significantly better. IMPORTANT: All 8bit samples in the dataset are tagged with fewP . You can add it to the negative/positive depending on whether you prefer that type of Pixel Art . All "higher quality" 16bit+ samples are tagged with manyP Try lowering CFG if everything is too "melty"Will start adding visible effects at 0.35+ Works great in the 0.4 - 0.8 range, depending on your preference and Lora MixI recommend 1+ for best "Pixel Art" results, if you are not going to mix it with other Loras.Few of the images in the gallery are with the final epoch that was overbaked, but still produced interesting results. If anyone is interested I will upload it as well as a separate version.

Pixel Art (Pony, SDXL)

The Lora is trained on MidJourney Images that use my "Personalised Style" + Pixel ArtWorks without the trigger words ArsMJStylePony, Pixel Art, manyP, fewP IMPORTANT: All 8bit samples in the dataset are tagged with fewP . You can add it to the negative/positive depending on whether you prefer that type of Pixel Art . All "higher quality" 16bit+ samples are tagged with manyPTry lowering CFG if everything is too "melty"Will start adding visible effects at 0.35+ Works great in the 0.4 - 0.8 range, depending on your preference and Lora MixI recommend 1+ for best "Pixel Art" results, if you are not going to mix it with other Loras.Few of the images in the gallery are with the final epoch that was overbaked, but still produced interesting results. If anyone is interested I will upload it as well as a separate version.

SDXL

Pony

Files with SHA256: d10351f5259d2afbe3b334a936f2007c1a53ca5c680046c75ab7bf6ef2909b4e