README

For best outputs:

  • Sampler: Euler a / DPM++ 2M Karras

  • Steps: 28, cfg 7, CLIP skip 2.

  • VAE: it has its own VAE, called boomer_vae.safetensors.

  • Features

    1. High-resolution images: Trained on 1024x1024 images (default for XL).

    2. Various art-styles: Multiple artists/illustrators from the 1970s - 1990s. A list of artists tags can be found bellow.

    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. 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. Flexible: Can be easily merged with other SDXL checkpoints / LoRAs for more expansive generations.

    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.

  • Usage

    Special Tokens:

    • BAStyle, a general prefix that is not strictly required but can help maintain the models style.

      • Place at beginning of your prompt.

    Artist Tags: 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.

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

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

    • by Gladius

For best outputs:

  • Sampler: Euler a / DPM++ 2M Karras

  • Steps: 28, cfg 7, CLIP skip 2.

  • VAE: it has its own VAE, called boomer_vae.safetensors.

  • Features

    1. High-resolution images: Trained on 1024x1024 images (default for XL).

    2. Various art-styles: Multiple artists/illustrators from the 1970s - 1990s. A list of artists tags can be found bellow.

    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. 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. Flexible: Can be easily merged with other SDXL checkpoints / LoRAs for more expansive generations.

    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.

  • Usage

    Special Tokens:

    • BAStyle, a general prefix that is not strictly required but can help maintain the models style.

      • Place at beginning of your prompt.

    Artist Tags: 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.

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

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

    • by Gladius

Actions
RUN
About
No description provided.
Updated on Mar 5, 2024
evevalentine2017/boomer-art-model-xl
Popularity
4 stars
235 runs
0 pulls
Maintainers
evevalentine2017