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
This lora contains every style (Type A,B,C,D,E) all in one package. The styles are triggered by using the tags:
memaxl6_a, memaxl6_b, memaxl6_c, memaxl6_d, memaxl6_eThis is a departure from the tagless approach of the past since making this kind of lora wouldn't be possible otherwise.
Thanks to using tags, each style is much stronger and more faithful to the source material. The tags also allow you to control the strength of each style better while also being able to mix and match styles.
Furthermore, I've included the unreleased type E in this lora. Type E was never released since the style too closely resembled Type A and D. I decided to include it in this lora just for fun.
FAQ
Comments (4)
If anyone is interested i tested the new LORA on 10 images using latest Wai model. Here is my findings. Keep in mind scores are IN COMPARISON to each other:
Memaxl6_A - 5/5 texture,5/5 Composition, 1/5 Hands, 2/5 BG
Memaxl6_B - 4/5 texture,4/5 Composition, 4/5 Hands, 3/5 BG + adds random flowers,adds random details to clothes
Memaxl6_C - 4/5 texture,4/5 Composition, 5/5 Hands, 5/5 BG
Memaxl6_D - 5/5 texture,3/5 Composition, 5/5 Hands, 4/5 BG + worse facial expression
Memaxl6_E - 5/5 texture,4/5 Composition, 4/5 Hands, 5/5 BG
Memaxv5 - 4/5 texture,4/5 Composition, 5/5 Hands, 5/5 BG
Type E is actually my favorite overall other than slight hand issues. I am genuinely surprised you haven't released it before.What was the training criteria for Type E if you dont mind me asking?
E was originally meant to be a mix of D and A. But at the time of training, I didn't notice a strong enough difference from what was already available. I just ended up adjusting A with some of the E data. This is around the time I first released D.
With some recent experimentation I'm doing with the Seele model, I've readjusted E with new data and decided to group it into this model. The current E heavily focuses on round pupils like you see in the first 3 images of this lora. I'm glad it has a noticeable influence in your results.
@Fish788 Yeah it is pretty good. i think a mix of A and C has potential to be the best. C has best Backgrounds and hands, A has best everything except backgrounds and hands.
The visual style is excellent, but introduces a lot of chaos in the background.