*Update: AutismMix 2.0 uses Autism Pony as it's base. Please read the update (About This Version) on the side for more information.
This lora was trained on 1,200+ images from Megami Magazine from late 2018 to early 2024. The base for this lora is Pony Diffusion V6 XL so you will need that model to use this.
To get the results you see in the images above, these are the settings I used.
Prompt(at the start): score_9, source_anime, official art, [your prompt] <lora:MeMaXL-000002:0.87> (using '1' seems to give worse results)
Negatives: 3D, CGI, render, photo, text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast,
Euler a
Steps: 35
CFG Scale: 7
Highres Fix: 4x-UltraSharp
These are just the settings I've tested so far, you might find something more effective. Yes, I'm aware of the text in every image. This is the result of the dataset used. I might go back and manual remove the text and retrain the data. Maybe....
","type":"LORA","poi":false,"nsfw":false,"allowNoCredit":true,"allowCommercialUse":"Sell","allowDerivatives":true,"allowDifferentLicense":true,"stats":{"downloadCount":542,"favoriteCount":72,"commentCount":6,"ratingCount":3,"rating":5,"tippedAmountCount":45198},"creator":{"username":"Fish788","image":null},"tags":["anime","sexy","female","style","cute","girls","2d anime"],"modelVersions":[{"id":332154,"modelId":269772,"name":"AutismMix v2.0","createdAt":"2024-02-06T23:10:12.155Z","updatedAt":"2024-02-06T23:13:34.729Z","status":"Published","publishedAt":"2024-02-06T23:13:34.727Z","trainedWords":[],"trainingStatus":null,"trainingDetails":null,"baseModel":"SDXL 1.0","baseModelType":null,"earlyAccessTimeFrame":0,"description":"This lora version was trained on 150+ images from Megami Magazine mostly from 2023 to early 2024. All of the images from the dataset have descriptive text in the corner, so I painstakingly went through and removed all the text from the corners of every image used.
My goal for the lora was to exceed the previous version completely. Well, it's more of a diagonal upgrade than a direct one. This lora was trained on Autism Pony instead of Base Pony and I tried using slightly different settings to accelerate the training. The results have been mostly positive, but noticeably different than the previous version.
The Good
-Better understanding of the prompt thanks to AutismMix
-No more annoying japanese gibberish in the corners
-The style is more consistent (A mix of the lora and the influence from AutismMix)
-Much improved backgrounds (I made sure to include detailed background images and it paid off)
The Bad
-Hands come out wrong more often than I like (this is a result of the dataset used, I tried to avoid this from happening but you can't win em all)
-Faces tend to lack detail the further away they are (this effect hires results)
-Due to the limited data I used, the style is noticeably different from the previous version, this might not be desirable for some
Over all, I am happy with the results. Some people might be wondering if I will go back and correct the remaining 1,000+ images to make a true version upgrade. The answer to that question is, no. No I will not.
Enjoy!
","vaeId":null,"stats":{"downloadCount":79,"ratingCount":1,"rating":5},"files":[{"id":263333,"sizeKB":223101.35546875,"name":"MeMaXL_V2.safetensors","type":"Model","metadata":{"fp":null,"size":null,"format":"SafeTensor"},"pickleScanResult":"Success","pickleScanMessage":"No Pickle imports","virusScanResult":"Success","virusScanMessage":null,"scannedAt":"2024-02-06T23:15:55.987Z","hashes":{"AutoV1":"07563634","AutoV2":"B252532B56","SHA256":"B252532B568C2F4EAE92583318914E7DE0452367DDFB693DF9B17563A009E834","CRC32":"2A8ECAD2","BLAKE3":"EB622402D81EFAACEC1A9F06682E391F91CB8C9CB6283850D9038E9BF889A09F","AutoV3":"D93AA90CF9322006B7A3EA65137F568910FA8BE9D90BF840B034A2EE56E76F00"},"downloadUrl":"https://civitai.com/api/download/models/332154","primary":true}],"images":[{"url":"https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f0419798-b5c7-4198-9dfb-183250de79a8/width=450/6343646.jpeg","nsfw":"Soft","width":1536,"height":2048,"hash":"UXKwn9~Cyrd?#u9btSR+N2Ntx]o|IVNZIqRR","type":"image","metadata":{"hash":"UXKwn9~Cyrd?#u9btSR+N2Ntx]o|IVNZIqRR","size":3806826,"width":1536,"height":2048},"availability":"Public","meta":{"ENSD":"31337","Size":"768x1024","seed":2393908772,"steps":29,"hashes":{"model":"821aa5537f","lora:MeMaXL_V2":"739feb3443"},"prompt":"score_9, source_anime, 1girl, red hair, brown skin, yellow eyes, crop top, flat chest, sweating, looking looking at viewer, licking green popsicle, light blush, hillside road, driveway, backpack, ocean, birds,