CoolFace
Modelpublic

nDimensional/Boomer_Art_Model-SDXL

sourceHugging Facecreativeml-openrail-mupdated 2y agoView on Hugging Face
3likes46downloads
Model Card

<style> .center { display: block; margin-left: auto; margin-right: auto; width: 1216; } </style>

<div align="center"> <font size="12"><span style="color:Red">B</span>A<span style="color:Blue">M</span><span style="color:Yellow">!</span></font><br> <font size="6"><span style="font-family:Comic Sans MS"><b>(Boomer Art Model)</span></b></font> </div>

<img src="img/v2_sample.png" alt="Sample Image v2" class="center"/>

1970s - 1990s Fantasy / Sci-fi illustrations for SDXL.

<!-- START SUPPORT --> <a href='https://ko-fi.com/M4M3ZBOIT' target='_blank'> <img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi3.png?v=3' border='0' alt='Buy Me a Coffee at ko-fi.com' /> </a> <!-- END SUPPORT -->

Features

  1. 1.High-resolution images: Trained on 1024x1024 images (default for XL).
  2. 2.Various art-styles: Multiple artists/illustrators from the 1970s - 1990s. <i>A list of artists tags can be found bellow.</i>
  3. 3.Easy to prompt: Stylization of simple prompts can be achieved with as little as one special token (trigger) appended to the end of your prompt.
  4. 4.True to source: Special attention was payed to insure that the artstyle(s) being generated are as close to the individuals artstyle as possible.
  5. 5.Flexible: Can be easily merged with other SDXL checkpoints / LoRAs for more expansive generations.
  6. 6.Full parameter fine-tune: This is a full parameter fine-tune of the original SDXL base 1.0 model. Both the U-Net and both text-encoders were tuned during training.

<b>General Information</b>:

  • —Base model - SDXL v1.0
  • —VAE - <a href="https://huggingface.co/madebyollin/sdxl-vae-fp16-fix">sdxl-vae-fp16-fix</a>
  • —Type - Full-parameter fine-tune, including text-encoders, float16 (fp16).
  • —Style - Painting, Drawling, Illustration, digital painting

Usage

Note: More artists have been addded in V2 and the special token is no longer strictly required. Model card will be updated to reflect these changes.

<b>Special Tokens</b>:

  • —BAStyle, a general prefix that is not strictly required but can help maintain the models style.
  • —Place at beginning of your prompt.

<b>Artist Tags</b>: Appending these tags to the end of your prompt will guide the model to generate an output in the style of the artist that's being tagged.

  • —by Boris Vallejo
  • —by Brom
  • —by Caza
  • —by Chris Foss
  • —by Clyde Caldwell
  • —by Col Price
  • —by Dave Dorman
  • —by Frank Frazetta
  • —sketches by Frank Frazetta
  • —by Kelly Freas
  • —by John Berkey
  • —by Gimenez
  • —by Ken Kelly
  • —modern art by Kirsi Salonen
  • —modern art by Kyu Yong Eom
  • —by Luis Royo
  • —by Michael Whelan
  • —by Mike Hoffman
  • —by Milo Manara
  • —by Moebius
  • —by Philippe Druillet
  • —by Sanjulian
  • —by Ted Nasmith <br>

<i>A wildcard can be found in the 'files'.</i>

<b>Random Style Generation (RSG) Token</b>: The following token (trigger) is a made-up artist that generates an image in the style of a random artist. <i>It's not perfect but can yield interesting results.</i>

  • —by Gladius

Limitations

BAM! inherits some (not all) of the limitations from the original SDXL v1.0 model.<br> <b>BIAS</b>: This model is bias towards paintings, drawings, and illustrations from the 1970s - 1980s.

<i>Future updates are already in the works to bring SDXL up to — and beyond SD1.5 standards. If you want to contribute, DM me at the discord thread linked above. My goal is to create fine-tunes on unique styles or concepts SDXL struggles with, expanding the pool of models for merging.</i>