README.md

---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
    1girl, medium hair, gothic dress, there are many red flowers in the room,
    red theme, upper body, looking at viewer, masterpiece, best quality, newest,
    late
  parameters:
    negative_prompt: >-
      nsfw, rating:sensitive, lowres, bad anatomy, bad hands, text, error,
      missing fingers, extra digit, fewer digits, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      blurry, artist name
  output:
    url: images/animaginexl3.0__00625_.png
- text: >-
    pvc figure of 1girl, cat hears, blue hair, parka, hood on, shorts, dark
    atmosphere, smoke around, looking at viewer, masterpiece, best quality,
    newest, late
  parameters:
    negative_prompt: >-
      flat color, nsfw, rating:sensitive, lowres, bad anatomy, bad hands, text,
      error, missing fingers, extra digit, fewer digits, cropped, worst quality,
      low quality, normal quality, jpeg artifacts, signature, watermark,
      username, blurry, artist name
  output:
    url: images/animaginexl3.0__00688_.png
- text: >-
    1girl, cat ears, petite, blue hair, parted bangs, white dress, shirt,
    wariza, sitting, dynamic angle, light smile, head tilt, looking at viewer,
    masterpiece, best quality, newest, late
  parameters:
    negative_prompt: >-
      nsfw, rating:sensitive, lowres, bad anatomy, bad hands, text, error,
      missing fingers, extra digit, fewer digits, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      blurry, artist name
  output:
    url: images/animaginexl3.0__00690_.png
- text: >-
    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, masterpiece, best quality, newest, late
  parameters:
    negative_prompt: >-
      nsfw, rating:sensitive, lowres, bad anatomy, bad hands, text, error,
      missing fingers, extra digit, fewer digits, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      blurry, artist name
  output:
    url: images/animaginexl3.0__00695_.png
- text: >-
    1girl, black hair, long hair, red scarf, trench coat, reaching towards
    viewer, looking at viewer, snowy, bokeh, masterpiece, best quality, newest,
    late
  parameters:
    negative_prompt: >-
      nsfw, rating:sensitive, lowres, bad anatomy, bad hands, text, error,
      missing fingers, extra digit, fewer digits, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      blurry, artist name
  output:
    url: images/animaginexl3.0__00696_.png
- text: >-
    1girl, red hair, cat ears, closed eyes, closed mouth, expressionless, maid
    costume, apron, lolita dress, frills, lying on back, sheets, red flowers,
    from above, masterpiece, best quality, newest, late
  parameters:
    negative_prompt: >-
      nsfw, rating:sensitive, lowres, bad anatomy, bad hands, text, error,
      missing fingers, extra digit, fewer digits, cropped, worst quality, low
      quality, normal quality, jpeg artifacts, signature, watermark, username,
      blurry, artist name
  output:
    url: images/animaginexl3.0__00698_.png
base_model: cagliostrolab/animagine-xl-3.0-base
instance_prompt: null
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
datasets:
- p1atdev/pvc
---

# pvcxl-v1-lora

PVC style LoRA trained on [cagliostrolab/animagine-xl-3.0-base](https://huggingface.co/cagliostrolab/animagine-xl-3.0-base).

<Gallery />



## Download model

Weights for this model are available in Safetensors format.

[Download](/p1atdev/pvcxl-v1-lora/tree/main) them in the Files & versions tab.

## Training details

### Dataset

Curated high quality 2.5k pvc figure images from [p1atdev/pvc](https://huggingface.co/datasets/p1atdev/pvc)

[p1atdev/pvc-quality-swinv2-base](https://huggingface.co/p1atdev/pvc-quality-swinv2-base) was used to curate images.

### Training Config 

|Configuration Item||
|:-|-|
|IaaS|Compute Engine of Google Cloud Platform|
|Machine type|g2-standard-8 (8 vCPU, 32 GB RAM)|
|GPU|1 x NVIDIA L4|
|Dataset size|2576 images|
|Batch size|4|
|Training steps|1000+5000 (crashed and resumed)|
|Train text encoder|False|
|Image resolution|1024|
|Optimizer|AdaFactor|
|Learning rate|constant 1e-5 with 100 steps of warmup|