Type | |
Stats | 740 292 |
Reviews | (91) |
Published | Nov 10, 2024 |
Base Model | |
Training | Steps: 3,500 Epochs: 6 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Hash | AutoV2 F938844C3A |
These loras were trained on images from Megami Magazine from late 2018 to early 2024. Please read the About This Version for more information. Please use the lora based on the model for the optimum results.
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 Illustrious-XL v0.1.
V3 Type B: Trained using 52 images selected for their similar eyes and hair. Trained on Hadrian DeliceXL 2.0 and AutismMix .
V3 Type A: Trained using 50 images selected for their similar eye style and detailed backgrounds. Trained on AutismMix, Hadrian DeliceXL 2.0, Ponymagine , Illustrious-XL v0.1.
V2: This lora was trained using 150+ images that I painstakingly removed the japanese text from. Trained on AutismMix.
V1: Trained using 1,200+ images. (All I had.) Trained on Based Pony.
To get the results you see in the images above, these are the settings I used.
Prompt(Pony): score_9,score_8_up,score_7_up,score_6_up,source_anime, <lora:MeMaXL:1> [your prompt]
Negatives(Pony): mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,
Prompt(XL): highres,absurdres,masterpiece,best quality,(anime screencap:0.5),
Negative(XL): worst quality,bad quality,lowres,jpeg artifacts,monochrome,bad anatomy,censored,multiple views,4koma,simple background,blurry background
Sample: DPM++ 2S a
Steps: 24-26 (Whatever gives you the best results)
CFG Scale: 5-7
Extension: [sd-webui-color-enhance] set to 0.5 (this increases the saturation a bit)
Upscaling: Follow this method