!!! 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/9e4fda7bca2b544e4ed7aa4c277ede37
->
PRUNED VERSION
This version of AniVerse is the famous one from the last disastrous training. Luckily I managed to save the good things that came out of it.
Generally, it tends to follow the prompt better and, given the same steps, has more details.
Another positive thing is that random generations, in grayscale or black and white, have been drastically reduced!
I hope you enjoy :)
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 (39)
Most important thing is that everything is going the right way with your health !
Thank you so much Vik 🤗🤗🤗🤗
Agreed 100% :) Praying for you Samael!
thanks,I love this model!
thank you ❤️🤗
Has a massive girl bias, so great if you want to make anime girls, really bad if you want to make anything else as you're in a constant battle to try and stop it generating girls.
Totally true ;)
My advice is using negative prompt to avoid girls, female, woman ;)
Stable Diffusion is universally biased in favor of making images of pretty girls/young women, although most trained checkpoints push even further in that direction.
If you want male characters, in addition to negative prompting, the Gender Slider embeddings are extremely effective: https://civitai.com/models/89709
And if you want images with no people in them at all, all I can tell you is that you have chosen a difficult path.
now you have 3 guesses why there is no mentioning of 'man' in the model tags
Can we get a "skinny version" ? It takes half the prompt to turn her in a supermodel... :-)
Sorry, what do you mean?
AniVerse... It's incredible... It is like a giant sun around which Samael's models revolve, like a shining ruby in the center of a crown decorated with other precious stones, like the mythical Yggdrasil tree uniting all the works of this wonderful author ...
And now seriously. :) It's not perfect, but... very close to that. Perhaps the only drawback in its flexibility that can be noted is its excessive focus on women. Great job, Samael! Thanks!
I am always surprised at the new AniVerse update. It is really more beautiful than ever.
Thank you💯💯💯💯🙏👏👏👏
aniverse 💕👻
Why not sdxl? sd1.5 is dead
long short story: because I've a 2060 with 12gb of Vram.
I need to buy a totally new PC (actually mine is very very very old, 2th gen of an i9), and I'm saving money to buy it. I really hope to buy a new one at the end of 2024 or the begin of 2025
PS: Plus I'm not a big fan of SDXL, it follow better the prompt, but as a friend of mine says, models are soulless. In the sense that it is not possible to imprint a style like on the SD15.
SDXL have many restrictions, soo sooo sooo.
And, after all, there are many authors and artists (like me) who like SD models more than SDXL.
We don't need true realism of SDXL, it and art, SD models help us to make art on our not super new laptops or PCs.
So, you're not right!!!
For example, you don't have the freedom to manipulate and control your result in sdxl, compared with 1.5
@Samael1976 also mentioned the Vram issue, you need to have a very good GPU to run SDXL, or purchase an online service plan.
Using SDXL or 1.5 depends on what kind of work and result you aim to, but we can't say it's dead.
@scuti0 in real, I'm using SD and SDXL engine on my GTX1660Ti Mobile with 6gb gddr6. It's not so power/ram hungry.
Advances in technology do not necessarily follow consumer usage. Take betamax, for example. The resolution and fidelity of betamax was superior to VHS. However, the accessibility of VHS among the consumer base allowed it to eclipse betamax in the market.
SD 1.5 is far from dead, at least at this point. As long as there are creators like Samael willing to push the envelope of what SD 1.5 will do, there will be more checkpoints.
In some of my workflows, I might use an SDXL checkpoint to start off with, but referred to an SD 1.5 for facial detailing.
@aeronliru I can also use sdxl, but it's frustrating about the time of generations. By the way, my problem is not generate images, but find the correct paramaters for do a training of SDXL. I'm trying, but trust me, with 12gb of vram is very very hard (it's almost 2 months now that I'm trying again, again and again)
@Samael1976 I understand You.
As for me - I'm only painting some arts as hobbie, in 99.9% cases using SD models - from 118 models on my lpatop only 8 are SDXL, but I use them not so often.
i freakin hate sdxl, its bad, can't promt anythign I used to do with sd1.5, and just not my style, pony on the other hand is quite nice but different, so I still use sd1.5
See all the animation/movie on Civit ? nearly all of them are made with 1.5.
18 downvotes, impressive
@MatoCreates Skill issue tbh
@Samael1976 12gb vram is good enough, i got 11 :P
@aeronliru restrictions? where?
@pope_phred maybe try sdxl and see how much better it is, though sd3 will come soon anyway
@sulph I do give SDXL a try, nothing in my comment said I didn't. My point is people will tend to use the thing that is most accessible. SD1.5 will still have it's users who may not have the processing power. Plus, the modding base for the 1.5 model is probably larger at this time, until the creators get better hardware.
@sulph cuz you're really not right, man
@sulph nsfw for exampl and etc. yes, we have some models that deny restrictions, but, anyway.
Big THANKS for update!
You're awesome!!!
Looks fantastic!, saying that and prefacing by saying thank you for keeping at least 3.0 available to us mobile users. Do you think you will allow an updated version to be used here on civit anytime soon? I understand you earn well deserved money from the other generation sites so please don't feel as I am complaining 😉. Maybe when the next version comes out we can have the previous version here?
All the best and keep up the great work!
Q) Do you think you will allow an updated version to be used here on civit anytime soon?
A) It's not a my decision, but it's civitai that decide if put it in online service or not. All my models are "configured" to be played here in Civitai Generation Service by default
Q) I understand you earn well deserved money from the other generation sites
A) Really? I'd like it XD XD XD. But Anyway, Civitai will be always my first choiche ;) (or better, my first place where I publish is Ko-Fi, and after Civitai)
Q) Maybe when the next version comes out we can have the previous version here?
A) Like I said, I really don't know how Civitai choiche... so maybe... I really don't know
@Samael1976 thanks for your responses! 😁 the only reason I asked is because in the description it says only generation services were magespace and another one I don't remember. I did not know that civitai chooses which checkpoints it allows online. I've only done loras and I assumed because I could choose online generation checkpoints could too. Keep up the great work like I said. Maybe I'll go bug the devs on discord and push for more of your stuff🤪
@2018cfh really the only one that in this moment is paying me, is mage, all others 🤷🏻
So if finally I will can buy a new PC for a better training in the future, I must say thank you to all people who supporting me in ko-fi and mage.
This model is awesome! Loved it!
Thank you ❤️
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.