Sweet-mix
End of the road - After 22 versions and over 2 years, Sweet mix will no longer be updated as of Illust v1.4. Honest thanks to those who stuck around.
Sweet-mix is a text-to-image Stable Diffusion model that is mostly focused on the anime art style. The model itself is a merge of multiple other models, as i don't have neither the time, nor the hardware to train a model. Sweet-mix can be used for both SFW and NSFW images. I think my model is pretty nice, so feel free to give it a try.
MUST-HAVES FOR GREAT IMAGE GENERATION LIKE IN THE IMAGES:
These quality tags: masterpiece, best quality, high quality, detailed, absurdres
This negative prompt: ugly, bad feet, bad hands, bad art, ugly artstyle, bad anatomy, bad fingers, censor, censored, ugly, deformed, noisy, blurry, low contrast, photo, realistic ,watermark, username, text
VAE: SD XL VAE
Good artist styles to use: iwbitu, kesoshirou, shexyo, oroborus, mamiyama, kihou no gotoku dmc, seisui bar, kawase seiki, yuuji (and), shiokonbu, hitmanatee, ashraely, starmilk
And a great imagination :)
Tensor.art link: Sweet-mix - Illustrious/XL - v1.4 | Tensor.Art (free online generation)
Description
FAQ
Comments (11)
My most used checkpoint Now. Awesome work! However, I find the Nose usually become a realistic nose when [Denoising strength] is high. I had to mask (inpaint not masked) the nose when doing inpainting.
@www01750033sina Thanks for the praise. While using 4x-Ultrasharp with 0.6 denoising strength i have never encountered this problem, so tell me if it still persists.
@Manseo Well. It is not too realistic. but the original img is DOT_NOSE, white the generated img always not. Here is my sample. https://civitai.com/posts/354679.
Using FLAT version is okay. This only happened with non-flat version, for example ver. 19.
Anyway, It's not a big problem.
@Manseo @Manseo When using Highres.fix, I set denoising strength low unless I want a semi-realistic picture.
@www01750033sina Well, being semi-realistic is kind of what this version of the model is for.
- Sweet-mix normal line-up (examples: v1.7, v1.9, v2.1) is for 2.25-2.5 D image generation
- Sweet-mix flat line-up (examples: v1.8-flat, v2.0 flat) is for 2D anime-like image generation
- Swoonify is for cartoony image generation
it says that blessed-vae has a pickle. is it still safe to use?
@ali1905 The guy that made blessed vae (Nocrypt) has also made loads of other stuff so I would really doubt that it isn't safe. Again, If you dont want to download the vae I recommended, you can always just download some other one you trust more.
@Manseo for some reason the blessed vae makes everything too bright. do you have another vae you can recommend?
@ali1905 there's 2 versions of the vae. The second version (blessed2) is dimmer than the first
@Manseo alright, thanks for the fast reply
I will always be a fan of your models, but I only love the v17 models! then merge
Details
Files
sweetMix_v21.safetensors
Mirrors
entpnoonnaaa_Soft.safetensors
Jungt BUS - Weights Model.zip
Betty%20-%20Regina%20Ruiz%20%5BHey%20Duggee%20%2F%20Latino%5D%20-%20Weights%20Model.zip
Pr%C3%ADncipe%20Zuko-Prince-Pablo%20Andr%C3%A9s%20Ausensi%20Mart%C3%ADnez-Avatar%3A%20La%20leyenda%20de%20Aang-%20The%20Last%20Airbender%20(Latin%20Americ-American%20Spanish%20Dub-Espa%C3%B1ol%20latino)%20-%20Weights%20Model.zip
pornmasterProFP32V4_fp32V4.safetensors
mixtapeSalsa_v10FusOBakedVAE.safetensors
28DSTABLEBESTVERSION_28dv5.safetensors
10_v1010.safetensors
sortLycorisFromLORA_v30.zip
yinmixreal_v10.safetensors
yuzufinetune_v12.safetensors
Tr1st1n_M4ys.pt
mixRealistic_v10.safetensors
avatarStyle_v15.ckpt
sentryBotVoiceSoVits_v10.zip
entpnoonnaaa_Soft.safetensors
elegantrpganimemagic_v10.safetensors
kawaiiRealisticAsian_v04.safetensors
analogporn_v20.ckpt
foolkatGODOF_v1.safetensors
superHeroComicStyle_v10.ckpt
envyanimexl_v09.safetensors
entpnoonnaaa_Hard.safetensors
SLD.safetensors
mobaGameEquipment_v10.safetensors
paint_V17.safetensors
pornmasterProFULLV4_fullV4.safetensors
rosedrawnmix_v11.safetensors
sweetMix_v21.safetensors