Animesh - LoRa

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

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

The only authorized generative service website are:

Mage.Space • RenderNet.ai • Sinkin.ai • Graydient • Arcanium.art

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

Animesh - my first base model is up!

Like I said this is my first base model so... press on <3 and post your images ;)

-> It work good with close up portrait (1:1) or vertical (9:16) output

-> at medium - long distance, I suggest to use inpaint masking only the face for better results.

-> The LoRa FV (Final Version) have better results with wwanime_v10 model

or DreamShaper 6.31 Backed Vae + Add More Details

⬇Read the info below to get the same quality images🙏

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

Recommended Settings - VAE is included (but if you want use one, use the 840000 ema pruned)

Clip skip : 2

Upscaler : 4x-Ultrasharp

Sampler : DPM++ 2M SDE Karras

CFG : 5.5~8 (7 it give you better results)

Steps : 30+ (I suggest 50 for long complicated prompt)

Pos Prompt: (ultra realistic, best quality, masterpiece, perfect face)

Neg Prompt : (worst quality, low quality, fat, ugly)

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

Do you like my work? check out my profile and see what else!

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

For commercial use, please be sure to contact me

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.