You must be 18+ to visit this website
The content on this website is AGE RESTRICTED
Please confirm you are at least 18 years old of age. Otherwise leave the website.
Lodestone-Rock profile
Lodestone-Rock
18+
Lodestone-Rock
Furry Machine Learning Researcher
Подписаться
Общаться

Планы подписки

$5
USD в месяц
Supporter

a nice support for our hard work is appreciated, thank you!

perks: - secret subscriber channel - discord roles

not included: - chocolate cookies

1 подписчик Supporter
Разблокировать
$10
USD в месяц
Serious Supporter

thank you for your support! may your GPU temp be low and it/s be high

perks: - early access to development model (webui access) - secret subscriber channel - discord roles

not included: - chocolate cookies

1 подписчик Supporter ; Serious Supporter
Разблокировать
$20
USD в месяц
Golden Supporter

thank you so so much for the support! may your GPU temp be low and it/s be high.

perks: - early access development model (weight download) - early access to development model (webui access) - secret subscriber channel - discord roles

not included: - chocolate cookies

8 подписчиков Supporter ; Serious Supporter ; Golden Supporter
Разблокировать

Особенности

Подписавшись вы получаете:
  • Доступ к контенту на этой странице.
  • Поддерживать автора контента материально - единоразово или на регулярной основе.
  • Возможность общаться напрямую с автором контента через чат на сайте.
Lodestone-Rock

Hi everyone! We’re very excited to present the alpha of our pilot Flux model. This has been our f...

Комментарии
Нравится(1)
Не нравится(0)
Пост заблокирован прайс-планом $5, $10, $20 .s
Разблокировать План
Lodestone-Rock
Публичный пост
Model Download
The model is available from CivitAI here. https://civitai.com/models/588186
Check out fast inference at frosting.ai who helped sponsor this model!

Model Info
Bananastrike XL is a successor to CompassMix XL Lightning. Its primary goal was to improve upon several issues related to Compass. In our testing, it has shown to have particular improvements in. 
  • Overall reduction of noise issue compared to CompassMix.
  • Improvements to background fidelity, less 'compressed' looking images.
  • Improved saturation balance, reducing overblown images.
  • Greatly improves issue where it looks like painterly characters are superimposed onto photographs.
 The model still maintains much of the hallmarks of CompassMix XL Lighting, such as a high-level of natural language understanding, prompt coherence and a wide-range of art styles. The model has also retained much of the knowledge from base SDXL, leaving an enormous array of concepts that the model understands. Bananastrike is a very close relative of CompassMix, the same seed with the same prompt tends to provide very similar outputs, albeit it with a different style. 

Strengths & Weaknesses
During our evaluations of the model by ourself and the community, we find the following strengths and weaknesses in the model.

Strengths 
  • High-level natural language understanding with the ability to handle multiple concepts.
  • A good level of tag understanding, allowing for a mixture of prompt styling.
  • A wide range of art styles and following of art styles.
  • Great prompt coherence
  • Ability to do humans and anthros well, with a wide range of supported species.
Weaknesses 
  • Noisy looking images, especially with photo backgrounds and plain backgrounds
  • Scenes with duo and higher tend to have various anatomical problems.
  • The model tends to prefer shorter captions compared to longer more detailed captions.
  • We aim to improve upon these issues in future releases of our models.

Recommended Settings
We recommend using the following settings with our model for best results.
  • Resolution: 1024x1024
  • Steps: 8-12
  • CFG Guidance: 2.5
  • Sampler: Euler or Euler a
The model utilises the low guidance and steps due to it being an SDXL Lightning model. It's advised to keep your step count as well as your guidance low, whilst you may increase the step count if you choose to do so, there is a clear point of diminishing returns, therefore we recommend you to follow our recommended values here.
Prompting & Tips
Natural language usage is recommended as the model and SDXL in particular understands it. However, you are also welcome to use tagging as you please.
This model is based off of SeaArt, it's advised to use their quality tags. They provide an example of this from their HuggingFace page.
The model supports various levels of quality hints, from "masterpiece" to "worst quality". Be aware that "masterpiece" and "best quality" may lean towards nsfw content.
They provide other prompting tips on their HuggingFace page that may be applicable to the model, you can find that page below.

Credits
This model was developed by the Horizon Team, a team dedicated to creating high-quality furry AI models.
  • Lodestone Rock
  • Bananapuncakes
  • Thessalo

We also thank SeaArtLab for training the original SDXL furry model that was the basis of this merge.

Extra Funded Provided By:

Finally, we'd like to express our heartfelt gratitude to our wonderful Patrons who made this model possible:
You are awesome! Patron:
  • Nexus
  • Nothingburger1234
  • TheGreatSako
Serious Patron:
  • SunBee
  • Simon
  • AndriFox
  • Mobbun
  • Kadah
  • Zenko
Patron:
  • Joseph
  • Krazark
  • kcanis

We are currently experiencing issues with our Patreon, if you'd like to discuss ways to donate, you can contact us at our Discord server here.
You can give a direct PayPal donation via our PayPal link here.

Keep in Touch
You can reach us at our Discord server!

Enjoy the release everyone! Take care.
Комментарии  загрузка...
Нравится(1)
Не нравится(0)
Sign Up or Log In to comment on this post
Lodestone-Rock
Публичный пост

COMPASSMIX XL 

Model Download
The model is available from CivitAI here.

Check out fast inference of this model at frosting.ai, which is the primary sponsor of this model.

Recommended Settings
We recommend using the following settings with our model for best results.

  • Resolution: 1024x1024
  • Steps: 8-12
  • CFG Guidance: 2.5
  • Sampler: Euler or Euler a

The model utilises the low guidance and steps due to it being an SDXL Lightning model. It's advised to keep your step count as well as your guidance low, whilst you may increase the step count if you choose to do so, there is a clear point of diminishing returns, therefore we recommend you to follow our recommended values here.

Model Info
This model retained much of the knowledge from base SDXL, leaving an enormous array of concepts that the model understands while also understand a lot of furry concepts.

Strengths & Weaknesses
During our evaluations of the model by ourself and the community, we find the following strengths and weaknesses in the model.
Strengths

  • High-level natural language understanding with the ability to handle multiple concepts.
  • A good level of tag understanding, allowing for a mixture of prompt styling.
  • A wide range of art styles and following of art styles.
  • Great prompt coherence
  • Ability to do humans and anthros well, with a wide range of supported species.

Weaknesses

  • Noisy looking images, especially with photo backgrounds and plain backgrounds
  • Scenes with duo and higher tend to have various anatomical problems.
  • The model tends to prefer shorter captions compared to longer more detailed captions.


Prompting & Tips
Natural language usage is recommended as the model and SDXL in particular understands it. However, you are also welcome to use tagging as you please.
This model is based off of SeaArt, it's advised to use their quality tags. They provide an example of this from their HuggingFace page.
The model supports various levels of quality hints, from "masterpiece" to "worst quality". Be aware that "masterpiece" and "best quality" may lean towards nsfw content.
They provide other prompting tips on their HuggingFace page that may be applicable to the model, you can find that page below.

Credits
This model was developed by the Horizon Team, a team dedicated to creating high-quality furry AI models.

  • Lodestone Rock
  • Bananapuncakes
  • Thessalo


We also thank SeaArtLab for training the original SDXL furry model that was the basis of this merge.

Extra Funded Provided By:

Finally, we'd like to express our heartfelt gratitude to our wonderful Patrons who made this model possible:
You are awesome! Patron:

  • Nexus
  • Nothingburger1234
  • TheGreatSako

Serious Patron:

  • SunBee
  • Simon
  • AndriFox
  • Mobbun
  • Kadah
  • Zenko

Patron:

  • Joseph
  • Krazark
  • kcanis


You can also give a direct PayPal donation via our PayPal link here.

Keep in Touch
You can reach us at our Discord server!

Enjoy the release everyone! Take care.

Комментарии  загрузка...
Нравится(1)
Не нравится(0)
Sign Up or Log In to comment on this post

Статистика

10 подписчиков
3 поста

Цели

$400.0
ЦЕЛЬ БЫЛА
ДОСТИГНУТА!
New Caption Dataset, around 40-50K high quality text image caption
$700.0
ЦЕЛЬ БЫЛА
ДОСТИГНУТА!
another secondhand RTX 3090 for rapid prototyping

Другие Звёзды

Этот веб-сайт использует файлы cookie для улучшения вашего опыта во время навигации по нему. Продолжайте использовать этот веб-сайт как обычно, если вы согласны с использованием файлов cookie. Ознакомьтесь с нашей Политикой Конфиденциальности для получения подробной информации. Выбирая Принять, вы даете согласие на использование файлов cookie.

Файлы cookie необходимы для функционирования этого веб-сайта

Если вы не согласны с этим, вы не сможете использовать сайт и должны выбрать ниже опцию «Покинуть SubscribeStar».

Если вы согласны с нашей Политикой Конфиденциальности и даете согласие на использование файлов cookie, выберите ниже опцию «Принять использование cookie».
We do NOT sell any information obtained through cookies to third-party marketing services.