V4
Completely redesigned the logic and architecture of the model. It can be said that it is almost a new model not similar to previous merges, but it contains almost everything the same as the previous versions, with some exceptions.
Sampling method - Euler a
Schedule type - Normal (Automatic)
Sampling steps - 30
CFG Scale - 6
Prompt:
TAGS + NL
very awa, newest, recent, masterpiece, best quality, absurdres, highres, detailed, Neg. prompt:
worst aesthetic, worst quality, low quality, old, early, mid, ai-generated, ai-assisted, bad anatomy, artistic error, lowres, bad hands, signature, artist name, scan artifacts, jpeg artifacts, unfinished, watermark, logo, text, dated, username, web address, bad feet, censored, blurry, off-topic, bad proportions, bad perspective, what, meme, tagme, copyright name, resized, downscaled, source larger, ugly, aliasing, cropped, MD5 mismatch, moire, third-party edit, image sample, upscaled, third-party watermark, has bad revision, 4-koma,V3
Sampling method - Euler a
Schedule type - Normal (Automatic)
Sampling steps - 30
CFG Scale - 7
Prompt:
very awa, masterpiece, best quality, year 2024, newest, highres, absurdres, very aesthetic, amazing quality, high resolution, ultra-detailed, detailed, score_9, Neg. prompt:
S:
worst aesthetic, good quality, normal quality, low quality, bad quality, worst quality, mid, early, old, adversarial noise, ai-generated, ai-assisted, stable diffusion, lowres, low res, monochrome, clone, XL:
very displeasing, displeasing, bad anatomy, artistic error, lowres, bad hands, signature, artist name, multiple views, artist sign, worst aesthetic, worst quality, low quality, bad quality, scan artifacts, jpeg artifacts, lossy-lossless, ai-generated, stable diffusion, abstract, official art, old, 4koma, reference sheet, dakimakura \(medium\), turnaround, comic, greyscale, monochrome, sketch, unfinished, watermark, logo, text, dated, username, web address, bad feet, extra digits, fewer digits, extra arms, extra faces, multiple heads, missing limb, amputee, severed limb, mutated hands, distorted anatomy, worst detail, censor, worst aesthetic, good quality, normal quality, mid, early, adversarial noise, ai-assisted, low res, thumbnail, compression artifacts, censored, bar censor, mosaic censoring, blurry, off-topic, bad proportions, bad perspective, what, meme, tagme, copyright name, copyright symbol, resized, downscaled, source larger, ugly, aliasing, simple background, asymmetrical, concept art, cropped, bleed through, crease, bad aspect ratio, derivative work, MD5 mismatch, moire, third-party edit, image sample, upscaled, Waifu2x, unmoving pattern, third-party watermark, has bad revision, doesnotexist, bkub, Recipe:
Final = [
[
# Left branch
{
chromaxlMix_v331 + indigoFurryMixXL_noobaiEPS [α=0.5]
} + {
novaFurryXL_illustriousV40 + rouwei_v07Epsilon [α=0.5]
} [α=0.5]
] + [
# Right branch
{
[
ntrMIXIllustriousXL_xiii + voivodspell_v10 [α=0.5]
] + [
4thTailAnimeHentai_050 + hassakuXLIllustrious_v2 [α=0.5]
] [α=0.5]
} + {
waiNSFWIllustrious_v110 + [
ponymagine91_gamma + (
ponymagine91_gamma - animagineXLV31_v31 + waiNSFWIllustrious_v110 [α=1.0]
) [α=0.5]
]
} [α=0.5]
] [α=0.5]
] + [
Illustrious-XL-v1.0 + (
noobaiXLNAIXL_epsilonPred11Version - cyberillustrious_v16 + illustriousXL_v01 [α=1.0]
) [α=0.5]
]V2
What's new in the version?
Added normal Pony tag support.
Improved anthropomorphic anatomy.
Added ability to make good photorealistic generation.
Added:
waiNSFWIllustrious_v10
AnimagineXL v40
chromaxlMix_v331
bigLove_xl1
Prompt:
very awa, very aesthetic, masterpiece, best quality, amazing quality, newest, recent, absurdres, high score, great score, score_9, score_8_up, score_7_up, Neg. prompt:
worst aesthetic, good quality, normal quality, low quality, bad quality, worst quality, low score, bad score, average score, mid, early, old, Krabby Patty Model secret formula:
=== Base Model ===
base_model = noobaiXLNAIXL_epsilonPred11Version=== Reinforcing the "Illustrious" style. ===
illustrious_enhancement = waiNSFWIllustrious_v100 + ((cyberillustrious_v16 + bigLove_xl1) - illustriousXL_v01)=== Fine Tuning Styles (Anime/Pony & other mixes) ===
style_tuning = (((animagineXL40_v40 + ponymagine91_gamma - animagineXLV31_v31) + autismmixSDXL_autismmixPony - ponyDiffusionV6XL_v6StartWithThisOne) + (chromaxlMix_v331 - noobaiXLNAIXL_epsilonPred11Version))=== FINAL RECIPE ===
final_recipe = base_model + illustrious_enhancement + style_tuningnoobaiXLNAIXL_epsilonPred11Version
+ { [ waiNSFWIllustrious_v100 + (cyberillustrious_v16 + bigLove_xl1 – illustriousXL_v01) ]
+ [ ( (animagineXL40_v40 + ponymagine91_gamma – animagineXLV31_v31)
+ autismmixSDXL_autismmixPony
– ponyDiffusionV6XL_v6StartWithThisOne )
+ (chromaxlMix_v331 – noobaiXLNAIXL_epsilonPred11Version) ]
}
V1
BE SURE TO USE VAE SDXL
I WAS ABLE TO MERGE
PONY XL
ANIMAGINE XL
WAI ILLUSTRIOUS
CYBER ILLUSTRIOUS
NOOB EP
IT'S SUCH A HELL OF A MIX, BUT IT WORKS... AND IT WORKS WELL...
Model supports LoRA for all of the above models, making it extremely versatile.
These prompts are provided as an example and are based on the merge models. Feel free to modify them as you see fit.
Prompt:
very awa, very aesthetic, masterpiece, best quality, amazing quality, newest, recent, absurdres, score_9, score_8_up, score_7_up, Neg. prompt:
worst aesthetic, worst quality, worst detail, low quality, bad quality, normal quality, old, early, mid, Recipe: NOOB + ((WAI IL + CYB IL - IL) + (PONY + ANIMGN) - SDXL)
Description
FAQ
Comments (20)
Is this model merged with Animagine v4?
nope, 3.1
@voider I also wish there was a merge of nai and animagine 4.
@voider This is probably the best model I 've used that takes all loras well. If you update with Animagine v4 it'll blow every thing out of the water.
@3r3de Hi, thank you so much for your feedback! I'm busy right now, but I'll try to do it in my free time!
Now V2 with v4
Is there a specific VAE to use ? I only get noise as images
Hi, I only get noise when I'm not using SDXL VAE. You can try using pony vae because it's the same thing. If you don't have vae, you can go to the official SDXL release and download it from there. If you still have problems, write me your discord in the dm and I'll help you.
The SDXL VAE finetune works with it for me. I have to use either "direct lighting" or "indirect lighting" in some my prompts to get something that isn't high contrast with the default positive and negative prompts listed.
The built-in VAE is broken on that mix. Don't use built-in VAE from checkpoint and use official separate VAE "sdxl_vae.safetensors"
Shockingly powerful model, it's taking some time to get to grips with it but it might just be the most powerful model I've used
Amazing job
First off I love this model. It follows some styles quite well and the prompt adherence is great.
I don't know if it's something with the merge or what, but sometimes when I gen I see the words "Score" appear like a watermark or sometimes on clothing. It's something minor but just wanted report it to you. Overall this merge is really nice and I hope to see more from you.
I too have run into the problem of the word "SCORE" appearing in various places. Presumably this is because in other models this word carries no meaning, but in the pony model it improves quality and aesthetics. Since the model works as all merged models at the same time, it tries to add this text and improve the style.
You can just not add the "score" tags, and then the word will disappear, but the style will deteriorate. So it is better to add "text" and "watermark" tags to the negative prompt. It's not much, but it will help to solve the problem.
Can you merge the model big Love and Proteus Rundiffusion into it? That could result in a 2.5 D merge that would be quite nice.
I'm aiming for a model that can quickly change styles and not be tied to one particular one as it's a basic model, but I'll see what models you're talking about and maybe I'll add them.
@Omotumbe Added one of these models
Does it take a lot of time to add from big love and proteus rundiffusion into it?
It's not that I don't want to, it's just that I have my final exams at the university right now and I have no time at all.
Works well when it does, sometimes it just completely breaks the art style, seems to be very hit and miss, especially with Lora's illustrious ones sometimes totally break, pony lora's seem to hold up the best. Also doesn't understand all base pony prompts for some reason? Pretty good model overall.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.














