!!! UPLOADING/SHARING MY MODELS OUTSIDE CIVITAI IS STRICLY PROHIBITED* !!!
Check my EXCLUSIVE models on Mage.Space: AniMage PXL • AniReal PXL • Lucid Dream • AniMage SD1.5 • Realistic Portrait
SDXL - Pony: AniVerse PXL • AniMerge PXL • AniToon PXL • AniMics PXL • AniVerse XL
SD1.5: AniVerse • AniThing • AniMerge • AniMesh • AniToon • AniMics
Also in Collaboration with Shakker.ai
This model is free for personal use and free for personal merging(*).
For commercial use, please be sure to contact me (Ko-fi) or by email: samuele[dot]bonzio[at]gmail[dot]com
⬇Read the info below to get the high quality images (click on show more)⬇
Aniverse - is just the beginning!
This is a long shot project, I’d like to implement something new at every update!
The name is a merge of the two words: Animation and Universe (and a word pun: Any+Universe -> Anyverse -> Aniverse)
-> If you are satisfied using my model, press on ❤️ to follow the progress and consider leaving me ⭐⭐⭐⭐⭐ on model review, it's really important to me!
Thank you in advance 🙇
And remember to publish your creations using this model! I’d really love to see what your imagination can do!
Recommended Settings:
Excessive negative prompt can makes your creations worse, so follow my suggestions below!
Before applying a LoRA to produce your favorite character, try it without first. You might be surprised what this model can do!
A1111 my settings:
I run my Home PC A1111 with this setting:
set COMMANDLINE_ARGS= --xformers
if you can't install xFormers (read below) use my Google Colab Setting:
set COMMANDLINE_ARGS= --disable-model-loading-ram-optimization --opt-sdp-no-mem-attention
My A1111 Version: v1.6.0-RC-28-ga0af2852 • python: 3.10.6 • torch: 2.0.1+cu118 • xformers: 0.0.20 • gradio: 3.41.2
If you want activate xformers optimization like my Home PC (How to install xFormers):
In A1111 click in "Setting Tab"
In the left coloumn, click in "Optimization"
in: "Cross attention optimization" select: "xformers"
Press in "Apply Settings"
Reboot your Stable Diffusion
If you can't install xFormers use SDP-ATTENTION, like my Google Colab:
In A1111 click in "Setting Tab"
In the left coloumn, click in "Optimization"
in: "Cross attention optimization" select: "sdp-no-mem - scaled dot product without memory efficient attention"
Press in "Apply Settings"
Reboot your Stable Diffusion
How to emulate the nvidia GPU follow this steps:
In A1111 click in "Setting Tab"
In the left coloumn, click in "Show all pages"
Search "Random number generator source"
Select the voice: "NV"
Press in "Apply Settings"
Reboot your Stable Diffusion
If you use my models, install the ADetailer extension for your A1111.
Navigate to the "Extensions" tab within Stable Diffusion.
Go to the "Install from URL" subsection.
Paste the following URL: https://github.com/Bing-su/adetailer
Click on the "Install" button to install the extension
Reboot your Stable Diffusion
How to install Euler Smea Dyn and Euler Max Sampler:
In A1111 click in "Extensions Tab"
click in "Install from URL"
Under "URL for extension's git repository" put this link: https://github.com/licyk/advanced_euler_sampler_extension
Once installed click in: "Installed" Tab
Click in "Apply and quit"
Reboot your Stable Diffusion
Now at the end of the list of the sampler, you have the new sampler.
How to use ADetailer with Euler Smea Dyn and Euler Max Sampler:
In A1111 click in "txt2img" tab
Expand and click in "enable ADetailer"
Scroll down and expand "inpaint" section
Click and turn on "Use separate Sampler"
Now select: "DPM++ 2M Karras" (or your favourite sampler)
VAE: VAE is included (but usually I still use the 840000 ema pruned)
Clip skip: 2
Upscaler: 4x-Ultrasharp or 4X NMKD Superscale
Sampling method: DPM++ 2M SDE Karras
Width: 576 (o 768)
Height: 1024
CFG Scale: 3 -> Steps: 15
CFG Scale: 4 -> Steps: 20
CFG Scale: 5 -> Steps: 25
CFG Scale: 6 -> Steps: 30...and so on...
MY FAVORITE PROMPT:
(masterpiece, best quality, highres:1.2), (photorealistic:1.2), (intricate and beautiful:1.2), (detailed light:1.2), (colorful, dynamic angle), RAW photo, upper body shot, fashion photography, YOUR PROMPT, (highres textures), dynamic pose, bokeh, soft light passing through hair, (abstract background:1.3), (sharp), exposure blend, bokeh, (hdr:1.4), high contrast, (cinematic), (muted colors, dim colors, soothing tones:1.3), morbid
NEGATIVE PROMPT:
(worst quality, low quality), negative_hand-neg, bad-hands-5, naked, nude, braless, cross, sepia, black&white, B&W, painting, drawing, illustration
YOU CAN ALSO USE THESE NEGATIVE EMBEDDINGS:
5) For MEN images: girl, woman, female, tits, BadImage_v2-39000, negative_hand-neg, bad-hands 5
HiRes.Fix Setting:
I don't use Hi.Res fix because:
1) in my computer don't work
2) my models don't need it. Use txt2image, aderailer and the suggested upscaler in the resources tab.
If you still want use it, this is the setting sent me by MarkWar (follow him to see his creations ❤️).
Hires upscale: 1.5
Hires steps: 20~30
Hires upscaler: R-ESRGAN 4x + Anime6B,
Denoising strength: 0.4
Adetailer: face_yolov8n
How to install and use adetailer: Click Here
Inpainting Setting:
When you see that I used Inpainting on my images, I only modify the face (Hires Fix on my old PC doesn't work and got stuck). This is my setting:
Click in the tab img2img, than click on inpaint ->
Paint the face (only the face, neck, ears...) and after that set:
Inpaint masked
Only masked
Only masked padding, pixels: 12
Sampling steps: 50
Set: Only masked
Batch Size: 8
in the Positive Prompt write: (ultra realistic, best quality, masterpiece, perfect face)Than click on GENERATE
ControlNet & Prompt guide video tutorial:
Thanx to: tejasbale01 - Spidey Ai Art Tutorial (follow him in youtube)
Animesh Full V1.5 + Controlnet | Prompt Guide |
Do you like my work?
If you want you can help me to buy a new PC for Stable Diffusion!
❤️ You can buy me a (Espresso... I'm italian) coffee or a beer ❤️
This is the list of hardware if you are courius: Amazon Wishlist
I must thank you Olivio Sarikas and SECourses for their video tutorials! (I'd really love to see a your video using my model ❤️ )
You are solely responsible for any legal liability resulting from unethical use of this model
(*) MarkWar is authorized by me to do anything with my models.
(**) Why did I set such stringent rules? Because I'm tired of seeing sites like Pixai (and many others) that get rich on the backs of the model creators without giving anything in return.
(***) Low Rank Adaptation models (LoRAs) and Checkpoints created by me.
As per Creative ML OpenRAIL-M license section III, derivative content(i.e. LoRA, Checkpoints, mixes and other derivative content) is free to modify license for further distribution. In that case such is provided by licensing on each single model on Civitai.com. All models produced by me are prohibiting hosting, reposting, reuploading or otherwise utilisation of my models on other sites that provide generation service without a my explicit authorization.
(****)According to Italian law (I'm Italian):
The law on copyright (law 22 April 1941, n. 633, and subsequent amendments, most recently that provided for by the legislative decree of 16 October 2017 n.148) provides for the protection of "intellectual works of a creative nature", which belong to literature, music, figurative arts, architecture, theater and cinema, whatever their mode or form of expression.
Subsequent changes, linked to the evolution of new information technologies, have extended the scope of protection to photographic works, computer programs, databases and industrial design creations.
Copyright is acquired automatically when a work is defined as an intellectual creation.
Also valid for the US: https:// ufficiobrevetti.it/copyright/copyright-usa/
All my Stable Diffusion models in Civitai (as per my approval) are covered by copyright.
Description
You can find my model in MAGE:
https://www.mage.space/play/a89102d204a3df79e7cb53718f88eeed
->
PRUNED VERSION
First thing: I'm better!
The acute phase of inflammation I was experiencing has passed, so apart from my usual migraines (3/4 a week) I would say that everything is back to normal.
I sincerely thank everyone who spent a few words to wish me good health.
Secondly, this version of AniVerse didn't exist until last week.
We all have to thank my friend nuaion, who out of mercy, given my desperation (I'll explain later), literally saved me from burning the few neurons I had left here XD.
In summary?
After 35 days of training for the new AniVerse... it turned out to be crap!
I honestly don't know the reason, you want the dataset, you want that I lost all the presets I had created (in short, I accidentally deleted them out of desperation that the dreambooth wasn't working, see previous episode) and maybe I set something wrong. ..
After days of desperation trying to save what little good there was in the new training, he gave me an idea (which I fully agree with) to go back to the past a bit.
In what sense would you say?
In the sense that AniVerse was losing its soul a bit, and was becoming too "realistic".
So this version was born with the intent (I hope achieved) of a dive into the past and return more towards 2.5D graphics
In summary?
Thank nuaion, (follow him because his creations are among the most spectacular I've ever seen and, since you're at it, also try his model for SDXL which is fantastic) who perfectly merged two versions of AniVerse to ensure that he found the correct path and kindly provided me with the file!
In the meantime, I'm always trying to find a model that satisfies me with the new training.
Anything else to say?
Oh yes!
I love this version of AniVerse! and in the future I will try not to deviate too much from the 2.5D style and this style.
I will try to make time to create AniToon, AniMics and AniMerge based on this version of AniVerse in the next few weeks, but I can't promise you anything, because... because I'm working on a new project, which many of you have asked me about...
Enjoy this version of AniVerse and thanks again everyone!
---------------------------------------------------------------------------------------------------
Positive Prompt:
(best quality, masterpiece, colorful, highest detailed) YOUR PROMPT (ultra-detailed body), (light smile:0.3), moonlight passing through hair, (night beautiful background:1.3), (intricate details), (dynamic angle)
Negative Prompt:
1) Easy Negative, moles, freckles,
2) Bad-Images-39000, moles, freckles
---------------------------------------------------------------------------------------------------
ITA:
Signori e Signore, come al solito, ho tonnellate di cose da scrivere.
Primissima cosa: sto meglio!
La fase acuta di infiammazione che stavo vivendo è passata, per cui, a parte le mie solite emicranie (3/4 alla settimana) direi che è tornato tutto alla normalità.
Ringrazio sentitamente tutti coloro che hanno speso due parole per augurarmi buona salute.
Seconda cosa, questa versione di AniVerse, fino alla scorsa settimana non esisteva.
Dobbiamo tutti ringraziare il mio amico nuaion, che preso dalla misericordia, vista la mia disperazione (dopo vi spiego), mi ha letteralmente salvato dal bruciare qui pochi neuroni che mi sono rimasti XD.
In sintesi?
Dopo 35 giorni di training per il nuovo AniVerse... era venuto fuori uno schifo!
Sinceramente non so il motivo, vuoi il dataset, vuoi che ho perso tutti i preset che mi ero creato (in sintesi li ho cancellati per sbaglio preso dalla disperazione del dreambooth che non funzionava, vedi puntata precedente) e forse ho sbagliato di settare qualcosa...
Dopo giorni di disperazione nel tentativo di salvare quel poco di buono che c'era nel nuovo training, mi ha fornito un'idea (che condivido appieno) di tornare un po' nel passato.
In che senso direte voi?
Nel senso che AniVerse stava un po' perdendo la sua anima, e stava diventando fin troppo "realistico".
Per cui questa versione nasce con l'intento (spero raggiunto) di un tuffo nel passato e tornare più verso una grafica 2.5D
In sintesi?
Ringraziate nuaion, (followatelo perchè le sue creazioni sono tra le più spettacolari che io abbia mai visto e, visto che ci siete provate pure il modello per SDXL che è fantastico) che ha perfettamente fuso due versioni di AniVerse per far sì che ritrovasse la strada corretta e mi ha gentilmente fornito il file!
Io nel frattempo, sto sempre cercando di trovare un modello che mi soddisfi del nuovo training.
Altro da dire?
Ah sì!
Amo questa versione di AniVerse! e in futuro cercherò di non discostarmi troppo dallo stile 2.5D e da questo stile.
Cercherò di fare in tempo nel creare nelle prossime settimane AniToon, AniMics e AniMerge basate su questa versione di AniVerse, ma non posso promettervi nulla, perchè... perchè sto lavorando ad un nuovo progetto, che in tanti mi
avete chiesto...
Godetevi questa versione di AniVerse e grazie nuovamente a tutti!
---------------------------------------------------------------------------------------------------
Positive Prompt:
(best quality, masterpiece, colorful, highest detailed) YOUR PROMPT (ultra-detailed body), (light smile:0.3), moonlight passing through hair, (night beautiful background:1.3), (intricate details), (dynamic angle)
Negative Prompt:
1) Easy Negative, moles, freckles,
2) Bad-Images-39000, moles, freckles
---------------------------------------------------------------------------------------------------
FAQ
Comments (34)
Pruned soon pls? :D
pls read the releases note info ;)
@Samael1976 In my opinion, this borders on disrespect for the community. Why do you think it’s possible to force everyone to download the 5GB model, even those who never need that size?
@Unicom that's a little dramatic isn't it? it's not a disrespect, he'll surely upload it later... and full versions are good for training loras on
@Unicom all creators are free to upload their content to civitai as they see fit and it's way too eays to prune a checkpoint yourself locally. we of course recommend all uploaders to provide different variants for all users' needs, but please see this as a bonus not a requirement.
@eurotaku @Malessar As soon as I have unlimited fast Internet, I will be happy to listen to any advice on this matter. But now it takes me half a day to download the 5GB model. Thx
@Unicom I've already explained, in the comment after this one, why the pruned version is always going out a week later after the full. I don't force anyone, the only thing that you must do is have patience and wait a week more.
@Unicom and said in all sincerity? I think your behavior is nothing short of disrespectful and capricious. I don't think having to wait an extra week to get the pruned version is a tragedy. Furthermore, I always want to remember that complaining about having to wait an extra week, for a resource that costs the author time and money (because I want to remember that leaving a PC in training for 30 days affects the electricity bill) made available for free This is not adult behavior. I don't know how old you are, but I hope you are very young and that over time you can learn to respect the work of others and above all patience.
@Samael1976 If we were on equal terms, you could reproach me and look down on me. I have no idea why you make people with paid traffic and slow Internet wait a week. I think that you have never found yourself in such conditions, so you cannot understand what it is. Perhaps because of your young age.
@Unicom maybe you don't know that I've start using internet with a modem at 14.400 bps. I started using a computer with a commodore vic20 and after an Olivetti prodest PC1 with 9mhz of cpu.
So, don't speak with me about have patience, please.
@Unicom and about wait a week more, I reply again, that I've explained why I do that.
I will repost the comment after that.
cit myself: "The answer is very simple. I don't know how long you've been following me, but if you look I try to post with a fixed deadline of 1 new model per week (every Monday). There is only one small technical problem... to create a new (trained) model, like AniVerse or AniThing, they usually take an average of 30 days (training only excluding the rest of the work). If I published both the full and pruned models on the same day, I would not be able, in terms of timing, to publish a new model every week."
Why do you only post full model first only and make us wait a week for a pruned version.
The answer is very simple. I don't know how long you've been following me, but if you look I try to post with a fixed deadline of 1 new model per week (every Monday). There is only one small technical problem... to create a new (trained) model, like AniVerse or AniThing, they usually take an average of 30 days (training only excluding the rest of the work). If I published both the full and pruned models on the same day, I would not be able, in terms of timing, to publish a new model every week.
PS and just to say... I'm so late with the schedule, that I released AniVerse 3.0 earlier here, than on my Ko-Fi page, where all my preview models are usually found
Oh, new AniVerse 💕🥰
Mage.Space paid you so much that you have new PC ?
Nope, I've not the new PC and probably I will not buy a new one until the last of this year or the first months of the new one.
I'm trying to save all that I can, but is not easy, you know 1) divorce, 2) Rent) 3) Bills...
Mage.Space helps me to save some money and in the future buy a new PC
@Samael1976 Id help you build the funds to buy a new computer, at least a RTX 4090, and whatever else, if you are in the US stock market. I used to scalp in the US stock market and it was a simple way to make money traveling.
@dadadies Thank you for your help, but I live in Italy...
Really nice💯
Even the previous version which is close to reality is a work of art and I really like it❤❤❤
Your models have nothing to say, in one word they are amazing .
In my opinion, the writing language should be improved in the updates. For example, make a picture with simple words. Like pony, which is a turning point for models.
Of course, this is my opinion
Thanks🙏❤
Hi Luna! First of all, thank you <3.
I have never tryied pony, becuase I'm to busy to develops my models, and I've no time to try other models.
But probably I've understand what you means.
Using the tags was a my idea for a while and I'd like to implement in the future, but not in AniVerse, in AniThing for replicate the different styles.
Next version of AniVerse is already in "work in progress".
And next project that Iìve in my mind, will take sometimes...
But never say never ;)
@Samael1976 thank you. For all your hard work.💟
Also, I am always waiting for new versions.💯
I apologize that my English is also weak🙏:)
@LUNA_s13 younare welcome Luna, and I'm 100% sure that your english is much better than mine! (where are you from? just curiousity ;) )
@Samael1976 I am Iranian. But I live in Türkiye.
@LUNA_s13 a my prompt (the girl with red hair) is "an iranian girl" are you? 😝
@Samael1976 Traditional Iranian henna is different from Indian henna. It has a red color. And most of the girls use it because it has medicinal benefits besides color. I have never seen a non-Iranian pay attention to it. I was surprised.👍💯
@LUNA_s13 I have always been fascinated by other cultures. Those (rare) times that I manage to take a trip, I always start by studying, because I would never want to disrespect the population that will host me. I have never been to Iran, but a few years ago I saw some photos of Iranian women from the 70s that remained imprinted in my memory, because it looked like Italy (the women did not wear veils). Besides the fact that, speaking generally, the features, the skin color, and above all the eyes of Iranian women are among the most beautiful I have ever seen!
@Samael1976 I had to leave my country, which I love more than anything else in the world, to save my life. I hope we will overthrow this evil dictator soon. Our country, Iran, which is full of civilization and rich history, and people who are friends with all the people of the world, became hostages of a bloodthirsty regime. I know and believe that soon people will take power. This beautiful land will be opened to the people of the world so that everyone can travel there safely and be safe and see the beauty of my country and its people. This is my dream for which I fought and will fight.
@LUNA_s13 Much respect towards you! I hope that sooner or later your words can come true and thus create a better world, after which people can walk anywhere on the planet without borders whatsoever (I am a cosmopolitan)
@Samael1976 I thank you. We all owe it to people like you. If there were no people like you to support us and our voices were not heard during the Mehsa Revolution, the government would have shot thousands of people. We were very close to victory. Unfortunately, the biggest blow to us was from the western governments. Especially the current US government. who are friends with the Iranian people on the surface, but behind the scenes they support this terrorist government with all their might. The guns that shot us were made in England. Biden was releasing Ali Khamenei's blocked money so that they could hire terrorists and massacre young men and women in the streets. These are only a small part of the reality. I will never forgive them. And of course, I speak my mind and fight wherever I can. even here
I love this model! Wish your others were available for civit generation.
All my models (in inside setting here in civitai) are turned on for the civitai generation. It's a choice of civitai make them available or not.
@Samael1976 oh really? I did not know that, I've only made loras and have just assumed it did whatever option you picked. But I've only trained online also so what do I know lmao.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.