These loras were trained on images from <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/wiki_pages/megami_magazine">Megami Magazine</a> from late 2018 to early 2024. Megami Magazine has different styles of 2d images and I chose to separate them by types. (Hence Type A, B, C, etc.) Please read the About This Version for more information. Please use the lora based on the model for the optimum results.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><h3 id="short-list">Short List</h3>Type A-E:Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772/memaxl-flat-anime-style-noobillustriousponyxl">v6.0 A-E [Noob1-Vpred]</a>Type A:Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772">v5.0 A [WaiShuffle-Vpred]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1509565">v5.0 A [Noob1-Vpred] </a>| <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1122902">v4.0 A [Zootlustrious-v2]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=565027">v3.0 A [Hadrian DeliceXL]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=411310">v3.0 Type A [AutismMix]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=502956">v3.0 A [Ponymagine]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=919342">v3.0 A [Illustrious-v1]</a>Type B:Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1622345">v5.0 B [Noob1-Vpred]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1335746">v4.0 B [Zootlustrious-v2]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=628612">v3.0 Type B [AutismMix]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=598214">v3.0 Type B [Hadrian DXL]</a>Type C:Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1738469">v5.0 C [Noob1-Vpred]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1045741">v3.0 C [Illustrious-v1]</a>Type D:Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1857360">v5.0 D [Noob1-Vpred]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1389510">v4.0 D [Zootlustrious-v2]</a>Old:Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=332154">v2.0 [AutismMix] </a>| <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=304130">v1.0 [Pony]</a><h3 id="long-list">Long List</h3>V6 Type A-E: Trained using 228 images. Each type is separated by the following tags.<pre><code>memaxl6_a, memaxl6_b, memaxl6_c, memaxl6_d, memaxl6_e</code></pre>The base for this lora is <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">Noob 1.0 V-Pred</a>.V5 Type D: Trained using 53 images selected for their similar eyes. The base for this lora is <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">Noob 1.0 V-Pred</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1857360">v5.0 D [Noob1-Vpred]</a>V5 Type C: Trained using 29 images selected for their similar eyes. The base for this lora is <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">Noob 1.0 V-Pred</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1738469">v5.0 C [Noob1-Vpred]</a>V5 Type B: Trained using 52 images selected for their similar eyes and hair. The base for this lora is <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">Noob 1.0 V-Pred</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1622345">v5.0 B [Noob1-Vpred]</a>V5 Type A: Trained using 43-50 images selected for their similar eye style and detailed backgrounds. The base for this lora is <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1190596">Noob 1.0 V-Pred</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/989367?modelVersionId=1494366">WAI-SHUFFLE-NOOB Vpred 2.0</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1509565">v5.0 A [Noob1-Vpred]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772">v5.0 A [WaiShuffle-Vpred]</a>V4 Type D: Trained using 53 images selected for their similar eye style. Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/852957/zootlustrious-aesthetic-illustrious-xl-refinement">Zootlustrious v2</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1389510">v4.0 D [Zootlustrious-v2]</a>V4 Type B: Trained using 52 images selected for their similar eyes and hair Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/852957/zootlustrious-aesthetic-illustrious-xl-refinement">Zootlustrious v2</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1335746">v4.0 B [Zootlustrious-v2]</a>V4 Type A: Trained using 50 images selected for their similar eye style and detailed backgrounds. Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/852957/zootlustrious-aesthetic-illustrious-xl-refinement">Zootlustrious v2</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1122902">v4.0 A [Zootlustrious-v2]</a>V3 Type C: Trained on 58 images based on similar eye types. Compared to Type A and B, the eyes are more round and more slender. The base for this lora is <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL v0.1</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=1045741">v3.0 C [Illustrious-v1]</a>V3 Type B: Trained using 52 images selected for their similar eyes and hair. Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/402492/hadrian-delicexl">Hadrian DeliceXL 2.0</a>, and <a target="_blank" rel="ugc" href="https://civarchive.com/models/288584/autismmix-sdxl">AutismMix</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=628612">v3.0 Type B [AutismMix]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=598214">v3.0 Type B [Hadrian DXL]</a>V3 Type A: Trained using 50 images selected for their similar eye style and detailed backgrounds. Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/288584?modelVersionId=324619">AutismMix</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/402492/hadrian-delicexl">Hadrian DeliceXL 2.0</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/391659/ponymagine-91">Ponymagine</a> , <a target="_blank" rel="ugc" href="https://civarchive.com/models/795765/illustrious-xl">Illustrious-XL v0.1</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=565027">v3.0 A [Hadrian DeliceXL]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=411310">v3.0 Type A [AutismMix]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=502956">v3.0 A [Ponymagine]</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=919342">v3.0 A [Illustrious-v1]</a>V2: This lora was trained using 150+ images that I painstakingly removed the japanese text from. Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/288584?modelVersionId=324619">AutismMix</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=332154">v2.0 [AutismMix]</a>V1: Trained using 1,200+ images. (All I had.) Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/257749/pony-diffusion-v6-xl">Based Pony</a>.Links: <a target="_blank" rel="ugc" href="https://civarchive.com/models/269772?modelVersionId=304130">v1.0 [Pony]</a>

MeMaXL Flat Anime Style - Noob/Illustrious/Pony/XL

This lora was trained on <a rel="ugc" href="https://civitai.com/models/391659/ponymagine-91">Ponymagine</a> using the same resources as V3.0. I also tested it on <a rel="ugc" href="https://civitai.com/models/260267?modelVersionId=403131">Animagine XL V3.1</a> and it seems to work (somewhat) but I highly recommend you just use it on Ponymagine since it's the entire reason I made this version. I do not guarantee support for anything else.Out of all the MeMa loras I've made, this lora is the most faithful to the original style. If you want the authentic Megami Magazine style then I highly recommend you use this version. If you just want flexibility with ass and titties then use the Pony 3.0 version.

MeMaPA.safetensors

MeMaXL Flat Anime Style - Pony Lora

v3.0 A [Ponymagine]

v6.0 A-E [Noob1-Vpred]

v5.0 A [WaiShuffle-Vpred]

v5.0 D [Noob1-Vpred]

v5.0 C [Noob1-Vpred]

v5.0 B [Noob1-Vpred]

v5.0 A [Noob1-Vpred]

v4.0 D [Zootlustrious-v2]

v4.0 B [Zootlustrious-v2]

v4.0 A [Zootlustrious-v2]

v3.0 C [Illustrious-v1]

v3.0 A [Illustrious-v1]

v3.0 Type B [AutismMix]

v3.0 Type B [Hadrian DXL]

v3.0 A [Hadrian DeliceXL]

v3.0 Type A [AutismMix]

v2.0 [AutismMix]

v1.0

These loras were trained on images from Megami Magazine from late 2018 to early 2024.V3 Type A: Trained on 50 images selected for their similar eye style and detailed backgrounds. The lora is great at prompt comprehension, amazing backgrounds and decent hands and feet. I trained with a few images from V2 and some others from the 1200 dataset I prepared. More than anything, the style is different from V2 and V1, so use the version you like best. I call it "Type A" because I'm considering training different styles using different images from dataset. Trained on&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/models/288584?modelVersionId=324619">AutismMix</a>.V3 Ponymagine: This lora was trained on&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/models/391659/ponymagine-91">Ponymagine</a>&nbsp;using the same resources as V3.0. I also tested it on&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/models/260267?modelVersionId=403131">Animagine XL V3.1</a>&nbsp;and it seems to work (somewhat) but I&nbsp;highly recommend&nbsp;you just use it on&nbsp;Ponymagine&nbsp;since it's the entire reason I made this version. I&nbsp;do not&nbsp;guarantee support for anything else.&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/articles/5294">Please read this if you're wondering why I made this.</a>V2: This lora was trained on 150+ images that I painstakingly removed the japanese text from. (V1 is plagued with this, V2 and V3 had the text removed from the images) This version does well with characters and backgrounds. Trained on&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/models/288584?modelVersionId=324619">AutismMix</a>.V1: Trained on 1,200+ images. (All I had.) Trained on&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/models/257749/pony-diffusion-v6-xl">Based Pony</a>.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, &lt;lora:MeMaXL_V3:1&gt; [your prompt]Negatives: mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,Sample: DPM++ 2S aSteps: 26 (Whatever gives you the best results)CFG Scale: 7Extension: [sd-webui-color-enhance] set to 0.5 (this increases the saturation a bit)Upscaling:&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/articles/4560">Follow this method</a>I exclusively use&nbsp;<a target="_blank" rel="ugc" href="https://civitai.com/models/288584?modelVersionId=324619">AutismMix</a>&nbsp;and I recommend you do the same. All of the examples were made with that model.

Ponymagine

Files with SHA256: 8d3b3f0b0957040cee8312c01892e37ab79c157768a492f6865b53952adf2911