Cetus-Mix
NOTICE:LET ME KNOW before you put this model on commercial usage.
My twitter account:@eagelaxis :) Contact me if needed.
Discord Account:Eagelaxis#7818
Hard to tell how many models used to merge.
Check the example images to recognize this model's art style
For more example images, just take a look at https://pixai.art
More attention on shades and backgrounds compared with former models(Andromeda-Mix | Stable Diffusion Checkpoint | Civitai)
Hands-fix is still waiting to be improved.
Highres-fix(upscaler) is strongly recommended(using the SwinIR_4x,R-ESRGAN 4x+anime6B by myself) in order to not make blurry images.
(Sorry for the misunderstanding caused by myself."Bad_prompt_v2:1.4" is a kind of embedding recognized as collection of normal negative prompts such as"lowres,bad anatomy".)
Recommend: Clip skip 2 Sampler:DPM++2M Karras Steps:20+
CFG scale:4-8 Vae:Pastel-Waifu-Diffusion.vae.pt(The vae used by Pastel-mix si just good enough)
Highres.fix:SwinIR_4x Hires steps:10+ Denoising strength:0.4+ Upscale by: 1.5+
Loras along with embeddings on hands-fix are strongly recommended.
V4 should be coming soon.
Looking forward to your reviews!
Versions
Rating | (36) |
Downloads | 23,923 |
Uploaded | Mar 08, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 BD518B9AEE |
This version is a special update of the original Cetus Series,and may be a little different from the style of Verison2 and 3.
Rating | (15) |
Downloads | 6,726 |
Uploaded | Mar 04, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 59EA4AA1D8 |
Mainly put more attention on potraits by reducing influence of some incorrect poses and meaningless shades.
If you have some suggestions or wishes for future update directions,please let me know in the reviewing area. :) I'll appreciate that.
There are other images I want to share but Civitai didn't let me upload,so I put them in my Pixai.
Rating | (16) |
Downloads | 4,635 |
Uploaded | Feb 27, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 56BE194F47 |
Rating | (30) |
Downloads | 7,519 |
Uploaded | Feb 06, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 E911995387 |
V2 changed some of the poses in order to make better human bodies and fix some bad hands(perhaps).
Rating | (3) |
Downloads | 615 |
Uploaded | Feb 06, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 163DF01063 |
V0 and V1's difference is mainly on composition of images.
Rating | (2) |
Downloads | 430 |
Uploaded | Feb 05, 2023 |
Base Model | SD 1.5 |
Hash | AutoV2 ED784495F9 |
Thanks for your support.