These loras were trained on images from Megami Magazine 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, these are the settings I used.
Short List
Type A-E:
Links: v6.0 A-E [Noob1-Vpred]
Type A:
Links: v5.0 A [WaiShuffle-Vpred] | v5.0 A [Noob1-Vpred] | v4.0 A [Zootlustrious-v2] | v3.0 A [Hadrian DeliceXL] | v3.0 Type A [AutismMix] | v3.0 A [Ponymagine] | v3.0 A [Illustrious-v1]
Type B:
Links: v5.0 B [Noob1-Vpred] | v4.0 B [Zootlustrious-v2] | v3.0 Type B [AutismMix] | v3.0 Type B [Hadrian DXL]
Type C:
Links: v5.0 C [Noob1-Vpred] | v3.0 C [Illustrious-v1]
Type D:
Links: v5.0 D [Noob1-Vpred] | v4.0 D [Zootlustrious-v2]
Old:
Links: v2.0 [AutismMix] | v1.0 [Pony]
Long List
V6 Type A-E: Trained using 228 images. Each type is separated by the following tags.
memaxl6_a, memaxl6_b, memaxl6_c, memaxl6_d, memaxl6_eThe base for this lora is Noob 1.0 V-Pred.
V5 Type D: Trained using 53 images selected for their similar eyes. The base for this lora is Noob 1.0 V-Pred.
Links: v5.0 D [Noob1-Vpred]
V5 Type C: Trained using 29 images selected for their similar eyes. The base for this lora is Noob 1.0 V-Pred.
Links: v5.0 C [Noob1-Vpred]
V5 Type B: Trained using 52 images selected for their similar eyes and hair. The base for this lora is Noob 1.0 V-Pred.
Links: v5.0 B [Noob1-Vpred]
V5 Type A: Trained using 43-50 images selected for their similar eye style and detailed backgrounds. The base for this lora is Noob 1.0 V-Pred and WAI-SHUFFLE-NOOB Vpred 2.0.
Links: v5.0 A [Noob1-Vpred] | v5.0 A [WaiShuffle-Vpred]
V4 Type D: Trained using 53 images selected for their similar eye style. Trained on Zootlustrious v2.
Links: v4.0 D [Zootlustrious-v2]
V4 Type B: Trained using 52 images selected for their similar eyes and hair Trained on Zootlustrious v2.
Links: v4.0 B [Zootlustrious-v2]
V4 Type A: Trained using 50 images selected for their similar eye style and detailed backgrounds. Trained on Zootlustrious v2.
Links: v4.0 A [Zootlustrious-v2]
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.
Links: v3.0 C [Illustrious-v1]
V3 Type B: Trained using 52 images selected for their similar eyes and hair. Trained on Hadrian DeliceXL 2.0, and AutismMix.
Links: v3.0 Type B [AutismMix] | v3.0 Type B [Hadrian DXL]
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.
Links: v3.0 A [Hadrian DeliceXL] | v3.0 Type A [AutismMix] | v3.0 A [Ponymagine] | v3.0 A [Illustrious-v1]
V2: This lora was trained using 150+ images that I painstakingly removed the japanese text from. Trained on AutismMix.
Links: v2.0 [AutismMix]
V1: Trained using 1,200+ images. (All I had.) Trained on Based Pony.
Links: v1.0 [Pony]
Description
Trained on 50 images from the Type A dataset. The base for this lora is Noob 1.0 V-Pred.
This lora uses slightly different and improved settings to accommodate for V-Prediction. V-Pred improves prompt comprehension and color range greatly. Noob has a nice range of concepts compare to Illustrious 0.1. You need to make sure you're using the proper UI and settings in order to utilize V-Pred. I don't expect this to work on Esp. models like Illustrious 0.1.
FAQ
Comments (10)
Are you able to give us your txt2img settings so I can plug it into pnginfo? Can't seem to replicate your images properly.
Due to the upscale method I use, the information on Civ or in the png isn't 100% accurate. Which image are you trying to replicate?
@Fish788 I just want to replicate any one of the sample images for the lora that uses Noob 1.0 V-Pred will do. I'm honestly trying to replicate the quality of the image. I've read through your settings guide that you posted, but everything looks drastically worse on my end, so I'm definitely doing something wrong. Would really appreciate it, thanks!
Here's a link to the raw text2img of the first pic of the Noob lora. https://files.catbox.moe/lwqw6p.png If you copy the png info and still get poor results, it might be due to some unsupported settings you have. It's very specific in what it wants.
@Fish788 thanks. still cant get any good results tho. But tbf i feel like on vpred models everything i try looks worse so it might be an issue with a111 even tho im on dev branch
@Wizzi Give Reforge a try. That's what i use and I've had no problems so far.
@Fish788 reforge has issues with LORAs. i have a massive list of LORAs and wildcards i changed names and reforge doesnt recognize them. For everyone that doesnt care about that that might b reading this in the future, thats what everyone should use though.
@Wizzi Issues with loras? I can't say I've had any problems with loras and I don't use wildcards, maybe the issue lies with the wildcard extension?
@Fish788 in forge and reforge if you renamed your LORA and try to call your LORA with that new name it breaks completely and ignroes all LORAs. unlike A111 which can read OLD AND NEW names and even if it cant read it will simply ignore that one LORA. Same with wildcards.
@Wizzi really? I wonder if that is what has been happening to me. I preferred auto1111 the most but I've been running forge just to use XL models and flux. I still have auto1111 installed but it used to crash a lot and forge was never crashing.