naclbit's picture
inference: true
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
license: creativeml-openrail-m

Please Note!

This model is NOT the 19.2M images Characters Model on TrinArt, but an improved version of the original Trin-sama Twitter bot model. This model is intended to retain the original SD's aesthetics as much as possible while nudging the model to anime/manga style.

Other TrinArt models can be found at:


The model has been ported to diffusers by ayan4m1 and can easily be run from one of the branches:

  • revision="diffusers-60k" for the checkpoint trained on 60,000 steps,
  • revision="diffusers-95k" for the checkpoint trained on 95,000 steps,
  • revision="diffusers-115k" for the checkpoint trained on 115,000 steps.

For more information, please have a look at the "Three flavors" section.


We also support a Gradio web ui with diffusers to run inside a colab notebook: Open In Colab

Example Text2Image

# !pip install diffusers==0.3.0
from diffusers import StableDiffusionPipeline

# using the 60,000 steps checkpoint
pipe = StableDiffusionPipeline.from_pretrained("naclbit/trinart_stable_diffusion_v2", revision="diffusers-60k")"cuda")

image = pipe("A magical dragon flying in front of the Himalaya in manga style").images[0]


If you want to run the pipeline faster or on a different hardware, please have a look at the optimization docs.

Example Image2Image

# !pip install diffusers==0.3.0
from diffusers import StableDiffusionImg2ImgPipeline
import requests
from PIL import Image
from io import BytesIO

url = ""

response = requests.get(url)
init_image ="RGB")
init_image = init_image.resize((768, 512))

# using the 115,000 steps checkpoint
pipe = StableDiffusionImg2ImgPipeline.from_pretrained("naclbit/trinart_stable_diffusion_v2", revision="diffusers-115k")"cuda")

images = pipe(prompt="Manga drawing of Brad Pitt", init_image=init_image, strength=0.75, guidance_scale=7.5).images

If you want to run the pipeline faster or on a different hardware, please have a look at the optimization docs.

Stable Diffusion TrinArt/Trin-sama AI finetune v2

trinart_stable_diffusion is a SD model finetuned by about 40,000 assorted high resolution manga/anime-style pictures for 8 epochs. This is the same model running on Twitter bot @trinsama (

Twitterボット「とりんさまAI」@trinsama ( で使用しているSDのファインチューン済モデルです。一定のルールで選別された約4万枚のアニメ・マンガスタイルの高解像度画像を用いて約8エポックの訓練を行いました。

Version 2

V2 checkpoint uses dropouts, 10,000 more images and a new tagging strategy and trained longer to improve results while retaining the original aesthetics.


Three flavors

Step 115000/95000 checkpoints were trained further, but you may use step 60000 checkpoint instead if style nudging is too much.



If you want to run latent-diffusion's stock ddim img2img script with this model, use_ema must be set to False.

latent-diffusion のscriptsフォルダに入っているddim img2imgをこのモデルで動かす場合、use_emaはFalseにする必要があります。


  • 8xNVIDIA A100 40GB

Training Info

  • Custom dataset loader with augmentations: XFlip, center crop and aspect-ratio locked scaling
  • LR: 1.0e-5
  • 10% dropouts


Each images were diffused using K. Crowson's k-lms (from k-diffusion repo) method for 50 steps.

examples examples examples


  • Sta, AI Novelist Dev ( @ Bit192, Inc.
  • Stable Diffusion - Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bjorn


CreativeML OpenRAIL-M