Tensor.Art
Create

Animesh

CHECKPOINT
Original


Updated:

406

⬇Read the info below to get the high quality images🙏 (click on show more)⬇

>>> UPLOADING/SHARING MY MODELS OUTSIDE CIVITAI IS STRICLY PROHIBITED <<<

This model is free for personal use and free for personal merging(*).

For commercial use, please be sure to contact me

////////////////////////////////////////////////////////////////////////////////////

Animesh - my first model!

This project at the moment is at the end, because I create Aniverse, a new project! Check my profile!

////////////////////////////////////////////////////////////////////////////////////

-> 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!

  • Try to use my model WITHOUT any "LoRa Model", it can give you a better result, trust me!

VAE: VAE is included (but usually I still use the 840000 ema pruned)

Clip skip: 2

Upscaler: 4x-Ultrasharp (rename the file extension from .pt to .pth and put the file 4x-UltraSharp.pth inside the folder "\YOUR~STABLE~DIFFUSION~FOLDER\models\ESRGAN\") (original credits by: Kim2091)

Sampler: DPM++ 2M SDE Karras

CFG: 5.5 (or less for 2D images) <-> 6+ (or more for 2.5D/3D images)

Steps: 20+ (I strongly suggest 50 for complex prompt)

-> For Humans portraits:

Height: 512px

Width: 912px

-> For Spaceships, Sport cars, Landscapes, ect:

Height: 912px

Width: 512px

Adetailer for Faces: face_yolov8n

-> (How to install and use adetailer: Click Here)

Pos Prompt: Use your best imagination. Usually I use (best quality, masterpiece)

  • SUGGESTED PROMPT: (best quality, masterpiece, perfect face) YOUR PROMPT, (hyper realism, soft light, dramatic light, sharp, HDR)

  • MY FAVORITE PROMPT: (best quality, masterpiece, perfect face, beautiful and aesthetic:1.2, colorful, dynamic angle, highest detailed face) YOUR PROMPT (high contrast, official art, extreme detailed, highest detailed)

Neg Prompt: ... No one! (This is why I said that I'm aiming for a "Easy Prompt")

  • Neg Prompt that I use (2): FastNegativeV2 and Bad-Hand-5 (nothing else, with these two I got the best results)

  • Neg Prompt (3): (worst quality, low quality) -> (To have the original model version and for an image that follow better your prompt)

  • Neg Prompt alternatives (4): BadImage_v2-39000 or Bad-Artist-Anime or Bad_Pictures or BadDream or EasyNegative 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)

  • Neg Prompt (5) (for MEN images): girl, woman, female, tits, BadImage_v2-39000

Better Hands (optional): Bad-Hand-5 (credits: yesyeahvh) or EnvyBetterHands LoCon

///////////////////////////////////////////////////////////////////////////////////

HiRes.Fix Setting:

Thanks to MarkWar (follow him to see his creations ❤️) that send me the HiRes.Fix setting and also for the beta testing:

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 *******)

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 (Expresso... 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.

Hide

Version Detail

SD 1.5
195000
1
THIS IS THE FINAL RELASE! (ALSO 2.0 Stable Release) Few things: -> Read the NEW description, because Positive Prompt and Negative Prompt are a little bit changed! (Sorry, but needed for the introducion of "Succubus, Vampire and "Dark Things" This is a total new training respect 1.X Respect 2.0 Beta: Much, much better the medium distance image and the prompt are more accurate! Next relase will be the Pruned Version and after (I try again) the Inpainting version. After that... I take a little break! XD PS: Over 65 hours (on my PC - 2060 with 12GB of ram) (Animesh 1.X was 30 hours) Over of 195.000 steps (Animesh 1.X was 110.000) Based on over 1300 high resolution images (Animesh 1.X was 700 images)

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.