Edit model card

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:

https://huggingface.co/naclbit/trinart_derrida_characters_v2_stable_diffusion

https://huggingface.co/naclbit/trinart_characters_19.2m_stable_diffusion_v1

Diffusers

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.

Gradio

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")
pipe.to("cuda")

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

dragon

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 = "https://scitechdaily.com/images/Dog-Park.jpg"

response = requests.get(url)
init_image = Image.open(BytesIO(response.content)).convert("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")
pipe.to("cuda")

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

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 (https://twitter.com/trinsama)

Twitterใƒœใƒƒใƒˆใ€Œใจใ‚Šใ‚“ใ•ใพAIใ€@trinsama (https://twitter.com/trinsama) ใงไฝฟ็”จใ—ใฆใ„ใ‚‹SDใฎใƒ•ใ‚กใ‚คใƒณใƒใƒฅใƒผใƒณๆธˆใƒขใƒ‡ใƒซใงใ™ใ€‚ไธ€ๅฎšใฎใƒซใƒผใƒซใง้ธๅˆฅใ•ใ‚ŒใŸ็ด„4ไธ‡ๆžšใฎใ‚ขใƒ‹ใƒกใƒปใƒžใƒณใ‚ฌใ‚นใ‚ฟใ‚คใƒซใฎ้ซ˜่งฃๅƒๅบฆ็”ปๅƒใ‚’็”จใ„ใฆ็ด„8ใ‚จใƒใƒƒใ‚ฏใฎ่จ“็ทดใ‚’่กŒใ„ใพใ—ใŸใ€‚

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.

ใƒใƒผใ‚ธใƒงใƒณ2ใฏ็”ปๅƒใ‚’1ไธ‡ๆžš่ฟฝๅŠ ใ—ใŸใปใ‹ใ€ใƒ‰ใƒญใƒƒใƒ—ใ‚ขใ‚ฆใƒˆใฎ้ฉ็”จใ€ใ‚ฟใ‚ฐไป˜ใ‘ใฎๆ”นๅ–„ใจใ‚ˆใ‚Š้•ทใ„ใƒˆใƒฌใƒผใƒ‹ใƒณใ‚ฐๆ™‚้–“ใซใ‚ˆใ‚Šใ€SDใฎใ‚นใ‚ฟใ‚คใƒซใ‚’ไฟใฃใŸใพใพๅ‡บๅŠ›ๅ†…ๅฎนใฎๆ”นๅ–„ใ‚’็›ฎๆŒ‡ใ—ใฆใ„ใพใ™ใ€‚

Three flavors

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

ใ‚นใƒ†ใƒƒใƒ—115000/95000ใฎใƒใ‚งใƒƒใ‚ฏใƒใ‚คใƒณใƒˆใงใ‚นใ‚ฟใ‚คใƒซใŒๅค‰ใ‚ใ‚Šใ™ใŽใ‚‹ใจๆ„Ÿใ˜ใ‚‹ๅ ดๅˆใฏใ€ใ‚นใƒ†ใƒƒใƒ—60000ใฎใƒใ‚งใƒƒใ‚ฏใƒใ‚คใƒณใƒˆใ‚’ไฝฟ็”จใ—ใฆใฟใฆใใ ใ•ใ„ใ€‚

img2img

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

latent-diffusion ใฎscriptsใƒ•ใ‚ฉใƒซใƒ€ใซๅ…ฅใฃใฆใ„ใ‚‹ddim img2imgใ‚’ใ“ใฎใƒขใƒ‡ใƒซใงๅ‹•ใ‹ใ™ๅ ดๅˆใ€use_emaใฏFalseใซใ™ใ‚‹ๅฟ…่ฆใŒใ‚ใ‚Šใพใ™ใ€‚

Hardware

  • 8xNVIDIA A100 40GB

Training Info

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

Examples

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

examples examples examples

Credits

  • Sta, AI Novelist Dev (https://ai-novel.com/) @ Bit192, Inc.
  • Stable Diffusion - Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bjorn

License

CreativeML OpenRAIL-M

Downloads last month
1,499
Inference API
Examples

Spaces using naclbit/trinart_stable_diffusion_v2 100