!!! 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/d8d5657480d78a0e0b3b8fafa7d55bde
->
PRUNED VERSION
This AniVerse version was literally the hardest model that I've made, but I also think it's also the best version out of all the ones released.
I have a lot of things to write, but I'll start by giving you the details for your creations, immediately after a short parenthesis.
Why the wording HD and 2.0? I imagine you're wondering.
HD: Because this version of AniVerse is trained (almost) entirely at 1024X1024px.
2.0: Because there is a slight shift towards an increase in realism compared to previous versions
////////////////////////////////////////////////////////////////////////////////////////////////////
This version gives you more scope for use.
You can use it as usual, to create 2.5D images in a semi-realistic, cartoonish or more realistic style.
It all depends on the positive prompt and negative prompt you will use.
You can find examples of prompts that I used.
In summary I can tell you that:
1) Bad-Images-39000 = More cartoonish images
2) Easy Negative and FastNegativeV2 = Usual Aniverse 2.5D style images
3) ng_deepnegative_v1_75t and EasyNegativeV2 = Images like the classic Aniverse, with a pinch of greater realism (not much)
////////////////////////////////////////////////////////////////////////////////////////////////////
But what does training at 1024px mean?
You can push your creations, with some peace of mind, to 1024x576 (or 1024x768) resolution, without using HiRes.fix. I went even further, up to 1280x720 with a margin of error of approximately ~5% (if you follow my advice):
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
I created over 1000 images to be sure and when I talk about an error rate of around 5% I naturally mean the classic elongated or double bodies due to too high resolution.
Sometimes three arms or three legs may appear, but it is another type of error, not related to resolution, so I excluded it from the error calculation.
If you want to avoid this kind of error, just go down to a resolution of 1024X576px, to return to a sort of safe zone.
The hands!!! I finally managed to improve the hands!!!
I said improve, but they are not yet perfect and I am very happy with the details that have been achieved in the creations.
There are other things that I would like to improve in the next version (or rather I'm already working to eliminate any cuts/artifacts that sometimes happen on the face)
I would also like to improve the angle of the shadows and other small things (like the teeth).
But I can say I am absolutely satisfied with this version.
Now a little chitchat to tell you how sweaty this version was.
The PC with which I'm training, every so often (I'm still trying to define the cause) decides to crash, so I have to turn it off and start training again (and sometimes I'm away from home and lose entire days).
The training lasted approximately 490 hours, which is equivalent to approximately 21 continuous days of training.
To find the fix for the hands, after having the final model, I worked on it for another 2 weeks.
I repeat, it was hard, long and difficult, more than a few times I thought about throwing everything away, but in the end, thanks also to a bit of luck, I managed to create this version of AniVerse which is truly satisfying me.
I hope it gives you the same satisfaction it is giving me.
We'll talk again soon... with a new project (which has already been in progress for a while, but at this time of writing, I haven't the faintest idea if it will lead to the desired results).
Samuel
////////////////////////////////////////////////////////////////////////////////////////////////////
Questa versione di AniVerse è stata letteralmente il modello più difficile da fare, ma penso anche che sia anche la versione migliore tra tutti quelli pubblicati.
Ho un sacco di cose da scrivere, ma inizio con il darvi subito i dettagli per le vostre creazioni, subito dopo una breve parentesi.
Perchè la dicitura HD e 2.0? Immagino che ve lo starete chiedendo.
HD: Perchè questa versione di AniVerse è allenata (quasi) totalmente a 1024X1024px.
2.0: Perchè c'è un leggero stacco verso un aumento del realismo rispetto alle versioni precedenti.
////////////////////////////////////////////////////////////////////////////////////////////////////
Questa versione vi da più margine di utilizzo.
Potete utilizzarla come al solito, per creare immagini 2.5D in stile semirealistico, cartoonistico oppure più realistico.
Tutto dipende dal prompt positivo e dal prompt negativo che userete.
Potete trovare gli esempi di prompt che io ho utilizzato.
In sintesi vi posso dire che:
1) Bad-Images-39000 = Immagini più cartonistiche
2) Easy Negative e FastNegativeV2 = Immagini solito stile di Aniverse 2.5D
3) ng_deepnegative_v1_75t e EasyNegativeV2 = Immagini come il classico Aniverse, con un pizzico di realismo maggiore (poco)
////////////////////////////////////////////////////////////////////////////////////////////////////
Ma il training a 1024px cosa comporta?
Beh, che potete spingere le vostre creazioni, senza HiRes.fix, con una certa tranquillità, fino a 1024X576px o 1024X720px. Io mi sono spinto anche oltre, fino a 1280X720px (e viceversa) con un error rate di circa il ~5% (se seguirete i miei consigli):
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
Ho creato più di 1000 immagini per essere sicuro e quando parlo di un errore rate di circa il 5% naturalmente intendo i classici corpi allungati o con doppio corpo dovuti ad una risoluzione troppo elevata.
A volte possono comparire tre braccia o tre gambe, ma è un altro tipo di errore, non legato alla risoluzione, perciò l'ho escluso dal calcolo dell'errore.
Se volete evitare questo genere di errore, basta scendere ad una risoluzione 1024X576px, per rientrare in sorta di zona sicura.
Le mani!!! Finalmente sono riuscito a migliorare le mani!!!
Ho detto migliorare, ma non sono ancora perfette e sono contentissimo dei dettagli che hanno raggiunto le creazioni.
Ci sono altre cose che vorrei migliorare nella prossima versione (o meglio sto già lavorando per eliminare eventuali tagli/artefetti che a volte capitano in faccia)
Vorrei anche migliorare l'angolazione delle ombre e altre piccole cose (come i denti).
Però posso dirmi assolutamente soddisfatto di questa versione.
Ora un po' di chitchat per dirvi quanto è stata sudata questa versione.
Il PC con il quale sto trainando, ogni tot tempo (sto cercando ancora di definire la causa) decide di impiantarsi, perciò mi tocca spegnere e ripartire con il training (e a volte sono fuori casa e perdo giornate intere).
Il traning è durato circa 490 ore, che equivalgono a circa 21 giorni continuativi di training.
Per trovare il fix delle mani, dopo aver avuto il modello finale, c'ho lavorato per ulteriori 2 settimane.
Ripeto, è stata dura, lunga e difficile, più di qualche volta ho pensato di buttare via tutto, ma alla fine, grazie anche ad un po' di fortuna, sono riuscito a creare questa versione di AniVerse che mi sta veramente soddisfacendo.
Spero che vi dia le stesse soddisfazioni che sta dando a me.
Ci risentiamo presto... con un nuovo progetto (che è già in corso d'opera da un po', ma in questo momento in cui scrivo, non ho la più pallida idea se porterà ai frutti desiderati).
Samuele
FAQ
Comments (88)
POSITIVE AND NEGATIVE PROMPTS ARE CHANGED. SO TAKE A LOOK TO HAVE BEST SETTINGS:
Sampling method: DPM++ 2M SDE Karras
Sampling steps: 50+ (minimum, it is very important not to go below this value)
Width: 576 (o 768)
Height: 1024
CFG Scale: 6~7
MY FAVORITE PROMPT:
(masterpiece, best quality, highres:1.2), (photorealistic:1.2), (intricate and beautiful:1.2), (detailed light:1.2), (soft lighting, side lighting, reflected light), (colorful, dynamic angle), upper body shot, fashion photography, YOUR PROMPT, dynamic pose, light passing through hair, (abstract background:1.3), (official art), (perfect skin), (sharp)
NEGATIVE PROMPT:
(worst quality:1.8, low quality:1.8), moles, mole, tears, piercing, freckles, skindentation, cutoffs, shiny skin, lucid skin, pendant, scars on face, interlocked fingers,
YOU CAN ALSO USE THESE NEGATIVE EMBEDDINGS:
1) Easy Negative, negative_hand-neg, EasyNegative, negative_hand-neg, moles, mole, piercing, tears, face skin imperfection, freckles, skindentation, cutoffs, shiny skin, scars on face, bad-hands-5
2) Bad-Images-39000, negative_hand-neg, moles, mole, piercing, tears, face skin imperfection, freckles, skindentation, cutoffs, shiny skin, scars on face, bad-hands-5
3) ng_deepnegative_v1_75t, (worst quality:1.4), (low quality:1.4), (normal quality:1.4), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), ((watermark)), negative_hand-neg, moles, mole, piercing, tears, face skin imperfection, freckles, skindentation, cutoffs, shiny skin, scars on face,bad-hands-5
4) (EasyNegativeV2:1.3), AloeCrapArt-1000-neg, negative_hand-neg, moles, mole, piercing, tears, face skin imperfection, freckles, skindentation, cutoffs, shiny skin, scars on face, tattoos, bad-hands-5
5) FastNegativeV2, negative_hand-neg, moles, mole, piercing, tears, face skin imperfection, freckles, skindentation, cutoffs, shiny skin, scars on face bad-hands-5
6) For MEN images: girl, woman, female, tits, BadImage_v2-39000, negative_hand-neg, moles, mole, piercing, tears, face skin imperfection, freckles, skindentation, cutoffs, shiny skin, bad-hands-5, scars on face, bad-hands 5
50 steps is pretty high. I was going with 20 before I read this and it was working pretty well for me. (Obviously 50 comes out better, but the difference isn't that huge. Especially if you're going to upscale it anyway)
But I've gotten great results with the suggested prompt. Thank you for including it along with the rest of the guide. It's so much easier when you have something to start from.
@imjustanotherguy in reality 50 steps are suggested if you want push over 1024*576, like for example 1280*720. Because with 50 steps it minimize errors in generations ;)
For those interested, I have updated my personal ko-fi page, with the next versions that will be published:
What is the difference between 1.6 and 1.5? I have been using 1.5 for awhile now and it is one of my favorite merge models
Please, click and expand in the "about this version", is all written inside. (right column if you are using the PC)
PS Aniverse is not a merge, is a trained one.
Thank you for your big work!!!
Thank to you to support me and send me this message. Trust me, for me, is really important have this kind of message :)
Dude i like your checkpoint very much but I'm having a hard time making my character look left and right, she looks very precisely in the middle of the screen. Do you have any solution suggestions?
No idea, but have you try in the prompt with "look away" or "watch away from POV" or something of similaR?
Try 'looking at viewer' in the negative prompt
@DizzyGamera Thank you for the tips ;)
Sorry guys, I change the suggested setting again (because i'm testing on a new version of AniVerse) I hope it work also with the older version.
New setting:
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:
1) Easy Negative, negative_hand-neg, bad-hands-5
2) Bad-Images-39000, negative_hand-neg, bad-hands-5
3) ng_deepnegative_v1_75t, bad-hands-5
4) FastNegativeV2, negative_hand-neg, bad-hands-5
5) For MEN images: girl, woman, female, tits, BadImage_v2-39000, negative_hand-neg, bad-hands 5
Why it is don't work with Civitai's generator? (like if I copy exact prompt, it's produce completely different style)
Because Civitai generator can't have a lot of setting like I've described in the model description (for example in the setting you can't choose NV).
If you want replica a my image you must have a your home PC.
Sorry about that, but I can't do nothing for that.
Great work! i love it!!!!!
i can't find the VAE File :(
There's a link in the instructions that downloads it...?
wait a second, I leave you the link in the next comment
PS: if you click in the model description there is the link (also for understand better how to use my model). But this is the link:
https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors
@Samael1976 Thank you very Much!!!!!
Bellissimo! I might be swapping my favourite version to the verse instead of the merge.
What is the difference between them really? Is it merge is just more realistic?
Hi Cap! AniVerse is a trained model, AniMerge is a merged one. The difference is a lot. It means, for doing AniVerse you start with a dataset of your images and for doing a model I spent only for training 20/25 days of working PC 24/24h. AniMerge is a merge between AniVerse and another existing model. Is more easy to made a merge model instead trained one. For the last question is: yes. Usually with AniMerge I follow the rule for a more realistic model, AniVerse is more cartonish and more 2.5D.
@Samael1976 thanks mate, you have become my favourite creator. I love the semi-realistic look. It's clear you love what you do and it shows with the effort you put in. I just wish I could help.
@CaptainKokomo sign this date: 12 february ;)
Before someone ask me: Pruned version will be available the next week .
But i wanna ask 🥺
@NoobFromEgypt lol
Thank you for new model!
Your model line is awesome!
Thank you for your comment! It's like the fuel to continue to do my work. Thank you so much :)
Hello, I want to ask about lighting I love the model but many times my characters seem to have lighting from the back which makes them seem in shadow, trying different prompts didn't help very much. Can you give me some hints? What should I do so it seems that the light is hitting the character from the front or that there are no shadows at all?
try with: (front light) or (light from front) and in negative prompt: (shadows on face)
@Samael1976 Thanks, I did not thought about (shadows on face) that should work nice. But I also found Light Control slider Loras by NextMeal and they work really well.
@Samael1976
I cannot overstress how impressed I am with your latest iteration. The detail you have managed to coax out rivals a lot of SDXL models. I am enjoying this so much.
Thanks, for your hard work and dedication (double thanks to your computer, you are probably heating your home with the amount if processing it had to crank this out!)
Thank you Pope! Really! This kind of comment give me the motivation to continue my work ❤️.
PS: the best is yet to come, get ready because on February 12th there will be some great news ;)
PS yesterday I got the electricity bill: 448€ 😭😭😭😭 (1400Kwh) (2 mount)
@Samael1976 Wow!... I think I'll just stick to making prompts and doing the occasional merge!
How to eliminate the backgrounds wavy stripes?
in the positive prompt: change (abstract background:1.3) in (flat color backround) or use the name of a city or place, like for example: (new yourk background) or (lake background)
Samael would you consider doing a lora for captain britain?! i can't get her outfit anywhere or anyhow :P
edit: hope you like my cap america comic post :P
Hi, even if I wanted to, believe me, I really don't have the time to do it...
A. is coming embrace yourself.
PS: Yes I see it and yes I like it ;)
pruned and HD be equivalent in quality or...?
absolutely the same quality. The difference is the weight of the file.
A. is coming, embrace yourself
I am always a bit amazed at how this model can be prodded into realism with a few of the right loras and embeddings. Maybe the most flexible model short of XL. Definitely one of the best overall!
Agreed. When v2.0 came out, I threw a bunch of styles at it, and was impressed with its versatility, with clarity that rivals SDXL in some cases.
Thank you so much at both of you ❤️. PS: A. is coming, embrace yourself!
A. is coming, embrace yourself...
An ANI to tame them, an ANI to find them, an ANI to seize them and chain them in the dark.
Power is nothing without control - Power is nothing without control - Power is nothing without control - Power is nothing without control - Power is nothing without control - Power is nothing without control - Power is nothing without control
Follow OP Notes! I just updated everything and it was a significant upgrade without the extra time spent in Hires.
Trust no one, A. is out there! Trust no one, A. is out there! Trust no one, A. is out there! Trust no one, A. is out there! Trust no one, A. is out there! Trust no one, A. is out there! Trust no one, A. is out there! Trust no one, A. is out there! Trust no one, A. is out there!
"I'm scared to close my eyes, I'm scared to open them...."
It's really coming, isn't it?
@Joen98 I'm already come, take a look in other models, I'm AniThing.
@Samael1976 I will create + review (NSFW)
@Joen98 PS if you will know me better, click on "about this version" and you will understand 🤗
I know there is a model online called Aniverse XL. I would like to underline that this model is not mine and that an XL version is not currently planned until I completely change my PC (we are talking about at least the end of 2024 and the beginning of 2025).
Why don't I create an XL version of my models?
Simply because I currently can't train an XL model with my hardware. I tried, but it would take 625 days to finish the model and it seems way too much to me.
So why not make a merge version of other models?
Because it's not my style. Taking models made by other people, and merging them, without putting anything "mine" into them is all too easy. I could create a different merge model every day, but what's the point if I can't put my own work in it? It would be like exploiting the work done by others and taking credit for it. Honestly, it's not my style or my way of thinking.
I want to underline that it is my thought, I understand whether it is acceptable or not, but all my models are born with the idea of bringing something "innovative" and merging other people's work, without giving a touch of my own, I don't I consider it so.
I really hope that this message of mine is not misunderstood.
Long life and prosperity
I've been testing SD15 models for 2 month now, for female character your model is the best in my opinion, it just right! good luck with your next project :)
@_Maximus_ Thank you so much! I will try to expand my models to another level right now. I really don't know what could happend, but just for saying, the first checkpoint saved at 10% is 8.5GB (without Vae). So probably next version of Aniverse will be out at the same time full and pruned (Because I really don't know how much people have a gpu with 12gb or vram, for run a 8.5gb of model).
Boys&Girls
This article is for you with all my love:
https://civitai.com/articles/4193
!!! ATTENTION PLEASE !!!
Guys&Girls, I'm sorry, but the next release of AniVerse will be delayed (and so also the other merrged models)
Unfortunately, the version I had been training for 15 days (and had reached the halfway point) gave an error of:
UNET-v1-BROKEN, VAE-v1-BROKEN. Model type UNET-v1-BROKEN
This had happened to me before, if you remember, but I still managed to save my work.
Unfortunately this time, despite managing to make the model work, it is not worth releasing it.
It was supposed to be version 3.0 with over 13000 images in the dataset (almost three times more than usual), but while it works, the new version returns images very similar to AniVerse 2.0
Examples here: https://civitai.com/posts/1549685
Therefore I preferred to stop everything and I will resume training tomorrow (since my computer crashed and everything is blocked remotely)
Guys, maybe is the end....
I'm very sad in this moment.
But it'snl all day that I'm trying to search a solution.
In summary? Dreambooth (the training software) no longer works for me. I have tried various versions of A1111 (from 1.6 to 1.8) 1.6 is the only one that works, but it runs very slowly, even though everything is installed correctly. To make you understand the training he presented me with over 1500 hours of training itself, unthinkable. 1.7 and 1.8 give me errors during training. I tried the Stability Matrix version and dreambooth gives me errors there too. Now I'm trying to install forge, but I'm really at my last resort and I don't know where to turn anymore. Seriously, I'm sorry, but this might be the end of my models.
Nothing works... at the moment I'm reinstalling totally the system... this is my last try.
I'm seeing a lot of people having similar issues with A1111 and Forge... I wonder if some updates (or lack thereof) in Python packages or CUDA software or NVidia drivers are responsible... 🤔
@TooLittleVRAM Trust me I'm going totally crazy. Now I'm doing a totally fresh installation of Windows and SD+Dreambooth+Python and bla bla bla.
I will update this message I hope sunday or monday
Push through. In the end, it will all be worth it. I know it's frustrating, but the end justifies the suffering,
Guys&Girls GOOD NEWS!!
After a totally fresh install of all my PC, Dreambooth start working againg!
The training is started and it seems work perfectly! ❤️
(650 hours left to finish it)
Guys&Girls GOOD NEWS!!
After a totally fresh install of all my PC, Dreambooth start working againg!
The training is started and it seems work perfectly! ❤️
(650 hours left to finish it)
Sorry guys&girls, but until Civitai will not improve the generation service (like for example with Hires fix and aDetailer) I prefere to remove my models from this service, cause a lot of people give me low stars review.
I hope that you can understand.
Hello Samael, I understand your view but would like to remind you that Aniverse has 4.95 stars out of 5. I enjoyed using this model (specifically v1.5) on the Civitai generator service. I think the images looked great, no need for hires fix and after detailer in my opinion. As you said, you fear people who are pickier leaving bad reviews if they don't have hires fix and after detailer enabled. I think you don't need to worry about them as you are 0.05 stars away from perfection. This is just my opinion but I would love if you reenabled this model for the Civitai generator service. Thanks for all your hard work once again
@PeterNjeim the problem is not Aniverse 2.0 (that wasn't possible using in civitai), look the 1.5 version, you will see the difference:)
believe me, it's not imperative, I'm still thinking about it. So if many people ask me for it, I will put it back.
@PeterNjeim PS sometimes, in civitai generation, it's selected a model but the rendering is made with another model. There are some bug that they must fix it.
I would also like to be able to keep using this Model, so far it is my favorite model that I have found on this sight and really like how cool the style is.
@Raven999666 Really, I'm thinking about it... let me think this week ;)
I'm very sorry about the bad reviews. AniVerse was my favourite checkpoint and it literally made my dreams come true. I use external apps to improve the resolution of civitai images and I assure your model is amazing. I didn't review it yet and I will now... I hope you add it back. Thank you for your great work.
@Yopsi88 more people write this kind of words, and it's probably that I change my mind and I turn it back ;)
Thank you ❤️
Ok guys&girls, I hear you. After I put back online my models ;)
@Samael1976 thank you very much! You are amazing. Btw if there is a way to support you (vía patreon or something) let me know. Im yet New to civitai and its hard for me to find the info. Gonna check again in case I can support you somehow.
@Samael1976 I just saw you have a Ko fi, i never used it but tomorrow I will register and support you. Thank you again!
just reopen to civitai and 2 stars review come: https://civitai.com/reviews/644582
Do you understand guys now?
@Samael1976 we understand but focuss in the serious criticism and be sure of your good work. Many of us value it.
@Yopsi88 yes I understand it, but for my models it's not good, because they go down from the model ranking page.
@Samael1976 I just tested the generator and it results in different images even with the same seed. If you use the same seed and prompt, it will use a cached image and immediately display it, but if you modify the prompt slightly, for example by changing (<prompt>:1.3) to (<prompt>:1.30), it should result in the same image but it will regenerate it instead of using the cached version. Ever since Civitai switched to a different backend generation provider, the results no longer match. This could be due to the backend switched between A1111 and ComfyUI, as those two handle prompts differently. The results in my opinion are worse now than they used to be, so I can see where you're coming from
@Samael1976 Civitai has switched to a new rating system, so individual bad reviews won't affect the rating since it's grouped into categories, in your case "Overwhelmingly positive". I think this means you can re-enable the generation for v1.5, imo
@PeterNjeim it's already enabled ;)
@Samael1976 1.5/1.5 pruned shows as disabled, but maybe Civitai changed it so that only one version is allowed to be enabled. They did that before when they were trying out a new provider, but now maybe the restriction is back in place
@PeterNjeim yes, this time is not my fault. I've enabled again all my models... but civitai...
30000 buzz bounty!!!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.