Sign In

IlluXionMix_v1

90
451
11
Updated: Dec 17, 2023
styleanimesexygamesfanartanime style
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
451
Reviews
Published
Nov 14, 2023
Base Model
SD 1.5
Usage Tips
Clip Skip: 2
Hash
AutoV2
CC47392644
Failed Generation Contest Participant
7ELIX's Avatar
7ELIX

NOTE:- In above preview images ad-detailer is not used

NOTE:- Vae not Baked ⚠️ (Use Vae according to your need)

Hires.fix is strongly recommended to use (Anime styles are mostly 2D and illustrated soo to add details/definition Hires.fix is always a must)

Ad-detailer is also highly recommended to get good hands (as anime styles are mostly 2D or illustration styled art which generally creates distorted hands)

🟧-----------------------------------------------------------------------------------------------🟧

IlluXionMix is a merge of different anime styled models.

IlluXionMix can generate good results using less prompt.

🟧-----------------------------------------------------------------------------------------------🟧

You can also generate images online using this model on:

Tensor.art

🟪-----------------------------------------------------------------------------------------------🟪

Socials

Follow me on Instagram:- https://www.instagram.com/blitzz.ai/

Follow me on Pixiv:- https://www.pixiv.net/en/users/99137352

🟪-----------------------------------------------------------------------------------------------🟪

Recommended Parameter/settings.

*Sampler:- DPM++ 2M karras (More detailed results), DPM++ SDE karras, Euler & Euler a(More clarity with smooth textures)

*Steps:- 20 is minimum and after 20 its on your choice (Average Steps usage is between : 20 - 40)

*CFG Scale:- 4 to 12 ( 7 Works the best )

*Resolution:- 512x512, 512x768, 768x512 etc (all types of resolutions are suitable)

*Vae:- kl-f8-anime2_fp16, Orangemix, ClearVAE, Blessed2.vae, animevae etc (its is basically based on you preference wether you like dark images, light images, strong colours, weak colours and so on)

*Upscaler:- R-ESRGAN 4x+Anime6b (works best for this)

*Hires Steps:- Use half of the steps you have used to generate the image in the hires steps

(Example : If you are using 30 steps for generating the image use 12 to 15 steps in the hires.fix)

*Denoising:- 0.3 to 0.7 of Denoising

*Clip Skip:- 2

🟪-----------------------------------------------------------------------------------------------🟪

Embeddings.

Easynegative, FastNegative, ng_deepnegative, verybadimagenegative, badhands