VAE

This is my v1 attempt at a finetune of SDXL's VAE and I also wanted to share the training script. The script itself can be found on github: https://github.com/kukaiN/vae_fine...

This is Ernesti echevalier, the main character in the original Japanese Light Novell, the animation Knights & Magic.Prompt: ernesti echevalier,tomgirl,1boy,male focus,smile...

SandMix features a rugged yet intense brush touch. Enjoy fun painting!Recommended Sampling methodDPM++ SDEDPM++ SDE Karras 描述: 训练词语: ...

A style based on the artstyle of Hajime SorayaAboutInspired by the works of renowned Japanese artist Hajime Sorayama, this LoRA captures the essence of his iconic art style. So...

Protonic+ is a merge of various merged checkpoints that depict scenes of nature and backgrounds (in general) in a very stylistic and pretty way. It's primarily anime-ish with a...

Caution: This is categorized as VAE, as we have no dedicated text encoder category.Clip-L fine-tune released by zer0int on huggingfacehttps://huggingface.co/zer0int/CLIP-GmP-Vi...

Caution: This is categorized as VAE, as we have no dedicated text encoder category.Clip-L fine-tune released by zer0int on huggingfacehttps://huggingface.co/zer0int/CLIP-GmP-Vi...

It's not Pony, it's genning with style!Ok, no it really is Pony, just heavily stylized. I merged several of my own LoRA's into the stellar model GetPhats' Pony Anime Lewdpocaly...

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...

kl-f8-anime1(fix of kl-f8-anime) + kl-f8-anime2 = kl-f8-anime3& Negative/Positive invert kl-f8-anime& Blurry versionmse840000_klf8anime3:mse840000_klf8animeというVAE類...

kl-f8-anime1(fix of kl-f8-anime) + kl-f8-anime2 = kl-f8-anime3& Negative/Positive invert kl-f8-anime& Blurry versionmse840000_klf8anime3:mse840000_klf8animeというVAE類...

Very good Asian realistic model, super real, welcome to use! Compared with the original model, Asian face correction was carried out to remove the AI sense and strengthen the s...

Type T: Thick Lines Anime StyleThis model has an anime style with thick lines and rich color and produces very high quality images and it's good for artworks. No detail or qual...

Trained from the popular Chinese GuoMan (国漫).Try online before downloading: https://tusiart.com/models/xe-guo-man-fluxParadigmFill in the specific concepts in the brackets:A ...

? IMPORTANT - PLEASE READ EVERYTHING ?YOU MUST USE ALPHA CLIP AS WELL. PLEASE DOWNLOAD IT BY CLICKING ALPHA CLIP AT THE TOP BAR. FOLLOW USAGE INSTRUCTIONS BELOW FOR INSTALLATIO...

2024-12-01 Update: Added inpainting version.Somewhere around 2.71̶̦̗̋́̓̍̓8̵̰͚̪͂̽͋́̂̃͛̕ D. Recursed Canvas is a less realistic, fantasy-oriented Stable Diffusion 1.5 model. This...

Anime base model trained from SDXL-base with dataset on 1.8M anime pictures. Cute, smart, flexible, yours!Yes, this is a new SDXL anime base modelOutperforms every other non-po...

Type D: Adorable Doll-Like Anime StyleThis model has a cute doll like style and produces very high quality images. No detail or quality enhancing loras needed to achieve high q...

Type A1: Vibrant Anime Style - Normal VersionType A2: Vibrant Anime Style - Kawaii VersionThis model is rich in color and lighting and produces very high quality images and it'...

I'm doing my best. It's okay if you don't like this model. I'm always doing my best! Just because I'm a beginner, I won't blindly shrink back. 描述: My hands ...