VAE

Dance of blades 描述: 训练词语: 名称: kl-f8-anime2_f...

描述: 训练词语: 名称: kl-f8-anime2_fp16.safetensors...

SABABA - Is an okay Ish model mergeIt's a merge between absolutereality_v181, Amedira-bV3, skylight4 , CoffeeWithLiquor(heat) and some loras.VAE: WD1-4-kl-f8-anime2-bless09.ckp...

Generates Anime like Images | Versatile | Can generate NSFW - Soft NSFW ImageRecommended Upscaler: R-ERSGAN 4x+ Anime6B, R-ERSGAN AnimeVideoRecommended Steps: Between 8 ~ 22 (H...

Models:v1.1 Bakedin VAE: KNXO's experimental crappy model mix with fixed Keys and clearvae 2.3 baked inV1.0: KNXO's experimental crappy model mix with original VAE from Anythi...

Due to requests from the community, I have decided to make my pony model, which I have only created for personal use, available to the community.As I am absolutely not a fan of...

怎么用/how to use/使用方法触发词/key word/キーワードpoi氵,图库不大 不到两千注重皮肤光泽主要就是要这个油润感database not that huge (just1700)this model focus on skinthe most imp...

model designed for manga-like images (monochrome/flat color)licensed under yodaynoThis license allows you to use the model, but only for non-commercial purposes. You cannot use...

A fusion style conceptual model based on "rabbit" is more supportive of my lora, that's all 描述: A blend of 10 nekopara Loras with a weight of 0.03 ...

makes a girl with a pikachu shirt 描述: 训练词语: 名...

It's been a while since my last checkpoint, but I was inspired by the wonderful Cyberrealistic v5 by the extremely talented Cyberdelia.I added a touch of my own ZetaBlend, as w...

Hello , here a train model after a few tries , it is an evolution from me 1st train lora i put a while ago ? i will probably try again soon to further trainer better this or us...

In the grim darkness of the far future, there is only war... and diffusion.NSFW Anime version can be found herePreambleWar and Diffusion (WnD) is the first release of my Warham...

MysticMelange is a merge model focusing the aspect of anime.Creates wide variety of characters and styles with prompts.Recommended Positive Promptsmasterpiece, high_quality, hi...

Trained based on anything v3.v20 version the resolution used for training is 640×640.Exceeding this resolution will result in severe disintegration of limbs.v40 version trainin...

Recommended Negative Reminder Words:Negative prompt: (worst quality:2),(low quality:2),(normal quality:2),lowres,watermark,(NSFW:1.2),(open mouth:1.6), (teeth:1.6),Steps: 20, S...

Can do both SFW/NSFW. Can do anime and semirealistic style images (not fully but partially).How to use model:Sampler - DPM++ 2M Karras (preffered. Personally, I use Euler SGMUn...

Works well with weight ~0.70. The character name trigger is required, other are optional.I think the best results are from the AnyLoRA Anime Mix model by Lykon but you can see ...

VAE To make image more brightness.VAE folder ~/models/VAEVAE work fine with my Checkpoint. 描述: 训练词语: ...

Not my model, from the huggingface repo. This is an excellent merge model, particularly in the middle blocks. Try it yourself - take your favorite model, and block merge this a...