metadata

license: other
thumbnail: >-
  https://s3.amazonaws.com/moonup/production/uploads/6305db1fcfbde33ef7d480ff/AWS1FulVrdoZGB-WIejqQ.jpeg
datasets:
  - p1atdev/pvc
language:
  - en
library_name: diffusers
tags:
  - stable-diffusion
  - safetensors
widget:
  - text: >-
      pvc, masterpiece, best quality, exceptional, 1girl, red hair, cat ears,
      red eyes, curly hair, long hair, maid costume, frills, upper body, looking
      at viewer, red flowers, indoors, beautiful view, medieval,
    example_title: PVC
  - text: >-
      figma, masterpiece, best quality, best aesthetic, 1girl, cat ears, blue
      hair, high ponytail, parted bangs, white shirt, dress shirt, short
      sleeves, shorts, looking at viewer,
    example_title: Figma
  - text: >-
      nendoroid, masterpiece, best quality, best aesthetic, 1girl, aqua eyes,
      baseball cap, blonde hair, closed mouth, earrings, green background, hat,
      hoop earrings, jewelry, looking at viewer, shirt, short hair, simple
      background, solo, upper body, yellow shirt,
    example_title: Nendoroid
  - text: >-
      pvc, masterpiece, best quality, best aesthetic, 1girl, bangs, bare
      shoulders, beret, black hair, black shorts, blue hair, bracelet, breasts,
      buttons, colored inner hair, double-breasted, eyewear removed, green
      headwear, green jacket, grey eyes, grey sky, hat, jacket, jewelry, long
      hair, looking at viewer, multicolored hair, neck ring, o-ring, off
      shoulder, rain, round eyewear, shorts, sidelocks, small breasts, solo,
      sunglasses, wavy hair, wet, zipper,
    example_title: Green jacket
pipeline_tag: text-to-image

PVC v4

This model is a latent diffusion model finetuned on Waifu Diffusion v1.5 beta 2.6 with PVC figure images. You can use Danbooru tags to generate images.

Downloads

pvc-v4-fp16.safetensors

2.58 GB

pvc-v4-fp32.safetensors

4.31 GB

Show all

Please use WD's vae to get good results!

Prompt guide

Highres fix is highly recommended.

Trigger words

pvc means the pvc material style but not needed always.
figma is the figure style that has joints, and more tend to be product thumbnail images. To get joints, please emphasize figma by 1.2 ~ 1.5 or use doll joints tag.
nendoroid means the style of chibi figures. Use with chibi to get better chibis.

Negative prompt

(worst quality, low quality, bad aesthetic, oldest), bad anatomy, bad hands, text, cropped, signature, blurry

Comparison to v3

masterpiece, best quality, best aesthetic, 1girl, red hair, cat ears, closed eyes, closed mouth, expressionless, maid costume, apron, lolita dress, frills, lying on back, sheets, red flowers, from above
Negative prompt: (worst quality, low quality, bad aesthetic, oldest), bad anatomy, bad hands, text, error, cropped, jpeg artifacts, signature, watermark, username, blurry
Steps: 18, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1166304922, Size: 512x768, Model hash: 0866b17d46, Model: pvc-v3-fp16, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires steps: 12, Hires upscaler: Latent

Examples

TODO: あとでやる

Training information

Parameter	Value
Service	Runpod
GPU	A4500
Script	kohya-ss/sd-scripts
Cost	about $10
Hours	about 30 hours
Dataset	about 18000 images from p1atdev/pvc
Resolution	768
Epochs	13
Optimizer	Lion
LR	1e-7
Scheduler	cosine_with_restarts
Train Batch Size	12

🧨 Diffusers

Using the 🤗's Diffusers library to run Stable Diffusion 2 in a simple and efficient manner.

pip install diffusers transformers accelerate scipy safetensors
pip install xformers

Using StableDiffusionPipeline:

import torch
from diffusers import StableDiffusionPipeline
model_id = "p1atdev/pvc-v4"
pipe = StableDiffusionPipeline.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
)
pipe = pipe.to("cuda")
pipe.enable_attention_slicing()
pipe.enable_xformers_memory_efficient_attention() # required
prompt = "pvc, masterpiece, best quality, exceptional, 1girl, cat ears, red hair, long hair, hairpin, swept bangs, yellow eyes, black jacket, white shirt, blue tie, white gloves, hand up, upper body, looking at viewer, buildings"
negative_prompt = "nsfw, nude, worst quality, low quality, bad aesthetic, oldest, bad anatomy"
image = pipe(
    prompt, 
    negative_prompt=negative_prompt,
    guidance_scale=7.0,
    num_inference_steps=20
).images[0]
# save image
image.save("pvc_figure.png")
# or just display it
# display(image)

Using StableDiffusionLongPromptWeightingPipeline:

import torch
from diffusers import DiffusionPipeline
model_id = "p1atdev/pvc-v4"
pipe = DiffusionPipeline.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    custom_pipeline="lpw_stable_diffusion"
)
pipe = pipe.to("cuda")
pipe.enable_attention_slicing()
pipe.enable_xformers_memory_efficient_attention() # required
prompt = """
pvc, anime, masterpiece, best quality, exceptional,
1girl, bangs, bare shoulders, beret, black hair, black shorts, blue hair, bracelet, breasts, buttons,
colored inner hair, double-breasted, eyewear removed, green headwear, green jacket, grey eyes, grey sky,
hat, jacket, jewelry, long hair, looking at viewer, multicolored hair, neck ring, o-ring, off shoulder, rain,
round eyewear, shorts, sidelocks, small breasts, solo, sunglasses, wavy hair, wet, zipper
""" # long prompt
negative_prompt = "nsfw, nude, worst quality, low quality, bad aesthetic, oldest, bad anatomy"
image = pipe(
    prompt, 
    negative_prompt=negative_prompt,
    guidance_scale=7.0,
    num_inference_steps=20
).images[0]
display(image)

License

This model is released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (https://undeleted.ronsor.com/) for help with the license.

WD1.5 と同じ Fair AI Public License 1.0-SD ライセンスです。生成サービスなどでこのモデルまたは派生モデルを使う場合は、サービスの利用者にモデルを公開する必要があります。詳しい/正確なライセンスは原文を参照ください。