AniVerse

You can find my model in MAGE:<a target="_blank" rel="ugc" href="https://www.mage.space/play/20a658c9b57e5916dc352793ccaa50db">https://www.mage.space/play/20a658c9b57e5916dc352793ccaa50db</a>-&gt; Hi everyone, as you may have noticed it's a busy time in my little world.I'm learning to train with XL (I don't know if you've seen that <a target="_blank" rel="ugc" href="https://civitai.com/models/522756/aniverse-xl">AniVerse XL</a> came out), AniVerse Pony XL and now I want to learn how to create a model for Pixart Sigma, as long as my video card allows me.For this reason my weekly Monday publications with a new model will probably be skipped.This version of AniVerse is therefore just a merge, designed not to leave all those who use Stable Diffusion 1.5 "alone" (including me).I particularly like the colors, details and dynamism. Too bad for the hands, which from my tests are not exactly the best.Let me know what you think.PS As soon as I have time I will write an article for those who have 3/4GB video cards and how to use XL in these video cards.

aniverse_v50Pruned.safetensors

V5.0 - Pruned

V5.0

V4.0 - Pruned

V4.0

V3.0 - Pruned

V3.0

V2.0 (HD) - Pruned

V2.0 (HD)

V1.6 - Pruned

V1.6

V1.5 - Pruned

V1.5

THX Ed. (1.4) - Pruned

THX Ed. (1.4)

V1.3 - Pruned

V1.3

V1.2 - Pruned

V1.2

V1.1 - Pruned

V1.1

V1.0 - Pruned

V1.0

⬇Read the info below to get the high quality images🙏 (click on show more)⬇&gt;&gt;&gt; UPLOADING/SHARING MY MODELS OUTSIDE CIVITAI IS STRICLY PROHIBITED &lt;&lt;&lt;This model is free for personal use and free for personal merging(*).For commercial use, please be sure to contact me////////////////////////////////////////////////////////////////////////////////////Website who support Aniverse:<ul><li>Omniinfer - Run this model for free on the AUTOMATIC1111</li><li>Plugger.ai - is a hub where you find ready-to-use AI models.</li></ul>////////////////////////////////////////////////////////////////////////////////////Leaderboard of my 3 best supporter:https://ko-fi.com/samael1976/leaderboard////////////////////////////////////////////////////////////////////////////////////Aniverse - is just the beginning!This is a long shot project, I’d like to implement something new at every update!First thing, the name is a merge of the two words: Animation and Universe (and a word pun: Any+Universe -&gt; Anyverse -&gt; Aniverse)Second thing I’d aiming for an “EASY PROMPT” (You will understand by reading the suggested positive and negative prompt below if you read on)////////////////////////////////////////////////////////////////////////////////////-&gt; 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:<ul><li>Excessive negative prompt can makes your creations worse, so follow my suggestions below!</li><li>Try to use my model WITHOUT any "LoRa Model", it can give you a better result, trust me!</li></ul>////////////////////////////////////////////////////////////////////////////////////A1111 settings:I highly recommend you to update your A1111, it got a really big update)I run my A1111 with this setting:set COMMANDLINE_ARGS= --xformersMy 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////////////////////////////////////////////////////////////////////////////////////VAE:&nbsp;VAE is included (but usually I still use the&nbsp;840000 ema pruned)Clip skip:&nbsp;2Upscaler:&nbsp;4x-Ultrasharp or 4X NMKD SuperscaleSampler:&nbsp;DPM++ 2M SDE KarrasCFG:&nbsp;5.5 (or less for 2D images) &lt;-&gt; 6+ (or more for 2.5D/3D images)Steps:&nbsp;20+ (I&nbsp;strongly suggest&nbsp;50 for complex prompt)-&gt; For Humans portraits:Height:&nbsp;904pxWidth:&nbsp;512px-&gt; For Spaceships, Sport cars, Landscapes, ect:Height:&nbsp;512pxWidth:&nbsp;904pxAdetailer for Faces:&nbsp;face_yolov8n-&gt; (How to install and use adetailer: Click Here)Better Hands (optional):&nbsp;Bad-Hand-5 (credits: yesyeahvh)Pos Prompt:&nbsp;Use your best imagination. Usually I use (best quality, masterpiece)<ul><li>SUGGESTED PROMPT: (best quality, masterpiece, perfect face)&nbsp;YOUR PROMPT, (hyper realism, soft light, dramatic light, sharp, HDR)</li><li>MY FAVORITE PROMPT: (best quality, masterpiece, perfect face, beautiful and aesthetic:1.2, colorful, dynamic angle, highest detailed face) YOUR PROMPT (official art, extreme detailed, highest detailed)</li></ul>Neg Prompt:<ul><li>Neg Prompt (1): FastNegativeV2 (nothing else, with this one I got the best results)</li><li>Neg Prompt (2): Easy Negative (nothing else, for a more realistic style and less saturated colors)</li><li>Neg Prompt (3): (worst quality, low quality) -&gt; (To have the original model version and for an image that follow better your prompt)</li><li>Neg Prompt alternatives (4): BadImage_v2-39000 or Bad-Artist-Anime or Bad_Pictures or BadDream or VeryBadImageNegativeV_1.3(one at time, not all together 😉. These negative embedding work very good, and give you different style of image, choose your favorite)</li><li>Neg Prompt (5) (for MEN images): girl, woman, female, tits, BadImage_v2-39000</li></ul>///////////////////////////////////////////////////////////////////////////////////HiRes.Fix Setting:I don't use Hi.Res fix because:1) in my computer don't work2) 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&nbsp;MarkWar&nbsp;(follow him to see his creations ❤️).Hires upscale: 1.5Hires steps: 20~30Hires upscaler: R-ESRGAN 4x + Anime6B,Denoising strength: 0.4Adetailer:&nbsp;face_yolov8nHow 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:<ul><li>Click in the tab&nbsp;img2img,&nbsp;than click on&nbsp;inpaint -&gt;</li><li>Paint the face&nbsp;(only the face, neck, ears...) and after that set:</li><li>Inpaint masked</li><li>Only masked</li><li>Only masked padding, pixels:&nbsp;12</li><li>Sampling steps:&nbsp;50</li><li>Set:&nbsp;Only masked</li><li>Batch Size:&nbsp;8 in the Positive Prompt write:&nbsp;(ultra realistic, best quality, masterpiece, perfect face)</li><li>Than click on&nbsp;GENERATE</li></ul>////////////////////////////////////////////////////////////////////////////////////ControlNet &amp; Prompt guide video tutorial:Thanx to: tejasbale01 - Spidey Ai Art Tutorial (follow him in *******)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:&nbsp;Amazon Wishlist////////////////////////////////////////////////////////////////////////////////////I must&nbsp;thank you&nbsp;Olivio Sarikas&nbsp;and&nbsp;SECourses&nbsp;for their video tutorials! (I'd really love to see a your video using my model&nbsp;❤️&nbsp;)////////////////////////////////////////////////////////////////////////////////////You are solely responsible for any legal liability resulting from unethical use of this model(*) MarkWar&nbsp;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.

Aniverse


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

AniVerse v5.0-Pruned.safetensors

5.0 - Pruned

Files with SHA256: 967aa8fdf682ca0f6d7cd471fe0cf7fe4b642bc9f3a909b8d394579d53600832