Stable Diffusion Models

Quick & Easy Torrent Downloading

apt update
apt install -y aria2
aria2c "<magnet URL here>"


Stable Diffusion


The main model is v1-5-pruned-emaonly.ckpt, meaning it only has EMA weights.


Download from HuggingFace. Fast, global CDN but you need to login and share your contact information with the repository.

Full EMA models here.

Stable Diffusion Inpainting

A model designed specifically for inpainting, based off sd-v1-5.ckpt. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, synthetic masks were generated and 25% of the image was masked.




Download from HuggingFace. Fast, global CDN but you need to login and share your contact information with the repository.

Alternatively, you could use this Google Drive link that the author of the WebUI shared:

Google Drive


StabilityAI has relased two autoencoders for Stable Diffusion.


Resumed from the original kl-f8 VAE checkpoint, trained for 313198 steps and uses EMA weights.


Resumed from ft-EMA and uses EMA weight. Trained for another 280k steps using a re-weighted loss, with more emphasis on MSE reconstruction (producing somewhat "smoother" outputs).

Waifu Diffusion

Trained on Danbooru, slightly NSFW.


Trained on 600,000 high-resolution Danbooru images for 10 Epochs.

The float16 version is smaller than the float32 (2GB vs 4GB). Always use float16 (unless your GPU doesn't support it) since it uses less disk space and RAM.







EMA weights here.


Trained 56,000 Danbooru images for 5 epochs.

Pruned Model

The full-size model was pruned to produce this model. Basically, all the unnessesary data was removed.

EMA Model

There is no difference between the EMA and Pruned models.

The creators have provided a web download, but it's very slow.


Another anime finetune. Designed to nudge SD to an anime/manga style. Seems to be more "stylized" and "artistic" than Waifu Diffusion, if that makes any sense.

The 60,000 steps version is the original, the 115,000 and 95,000 versions is the 60,000 with additional training. Use the 60,000 step version if the style nudging is too much.

See the comparison below.

60,000 Steps
95,000 Steps
115,000 Steps


Trained on 19.2M anime/manga-style images. This model seeks for a sweet spot between artistic style and anatomical quality.



Based off Waifu Diffusion v1.2, trained on the artist Hiten. More Info. I've heard people say this model is best when merged with Waifu Diffusion or trinart2 as it improves colors.

To use the model, insert Hiten into your prompt. For stronger results, append girl_anime_8k_wallpaper (the class token) after Hiten (example: 1girl by Hiten girl_anime_8k_wallpaper).

WD v1.2 and SD v1.4 Merged

WD merged back into SD, I don't know what the ratio is. This was one of the first merges out there.

NovelAI Leaked Models

On October 7th, NovelAI's server were hacked by some guy from 4chan. He stole their Stable Diffusion and GPT models. No user information/PII.

Part 1

55GB and contains the main models used by NovelAI, located in the stableckpt folder. I suggest using your torrent client to download exactly what you want or using this script. You can use this guide to get set up.

Part 2

103GB and contains more GPT models and in-development Stable Diffusion models. You don't really need anything in here.

Unlisted Models

There's quite a lot of unlisted .ckpt torrents out there. Use a DHT search engine to search for ".ckpt"


HuggingFace publishes community-submitted Dreambooth models. View them here.

It updates automatically twice a day.



For anthropomorphic figures.

Remacri Upscaler

For landscapes.


According to the developers, SwinIR achieves:

State-of-the-art performance in bicubic/lighweight/real-world image SR, grayscale/color image denoising, grayscale/color JPEG compression artifact reduction.

Get it on GitHub >

Face Restorers


GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Get it on GitHub >

Textual Inversion

HuggingFace publishes community-submitted textual inversion models. I created a seperate page to preview and download them.

It updates automatically twice a day.

Model Comparison