Model Introduction

This model is built upon the NoobAI-XL Epsilon-pred 1.1-version checkpoint. I further trained it using curated images from the daily trending lists of the artists' community, as well as artworks from my personal favorite artists.

Life Orb is an item from the Pokémon series, it boosts the damage dealt by the holder's damaging moves, it's my favorite item so I used it as the name of the model.

200 Epochs version have finished, I paused the text encoder training from the 100th Epoch to improve the generation quality of the model, , so it performs better on the artist styles that have been trained in previous versions. In addition, I have also uploaded some intermediate versions, trained for 15 epochs, 26 epochs, 31 epochs, 48 epochs and 67 Epochs, 97 Epochs, and 159 Epochs. Note that some artist styles are only trained after epoch 50.

Happy New Year!

Recommended Settings

Parameters

• CFG: 4 ~ 5

• Steps: 28 ~ 35

• Sampling Method: Euler or Euler a

• Resolution: Total area around 1024x1024. Best to choose from: 768x1344, 832x1216, 896x1152, 1024x1024, 1152x896, 1216x832, 1344x768

• Hires upscaler: R-ESRGAN 4x+ Anime6B

• Denoising strength: 0.2 ~ 0.4

• Artists tag: 1 ~ 3 (If you need more, please lower the sum of weight to within 3)

• Characters and Artists tag same as NoobAI-XL were used in training (Only include those that exist). You can query the corresponding tags in this link. For some artists, common names (such as Twitter IDs) are also valid.

Prompts

• Prompt Prefix:

masterpiece, best quality, newest, absurdres, highres, amazing quality, very aesthetic, year 2023, year 2024,

• Negative Prompt:

nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro

The open-source license for my model is the same as the one used by NoobAI-XL. Below is the license description:

Model License

This model's license inherits from https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0 fair-ai-public-license-1.0-sd and adds the following terms. Any use of this model and its variants is bound by this license.

I. Usage Restrictions

• Prohibited use for harmful, malicious, or illegal activities, including but not limited to harassment, threats, and spreading misinformation.

• Prohibited generation of unethical or offensive content.

• Prohibited violation of laws and regulations in the user's jurisdiction.

II. Commercial Prohibition

We prohibit any form of commercialization, including but not limited to monetization or commercial use of the model, derivative models, or model-generated products.

III. Open Source Community

To foster a thriving open-source community,users MUST comply with the following requirements:

• Open source derivative models, merged models, LoRAs, and products based on the above models.

• Share work details such as synthesis formulas, prompts, and workflows.

• Follow the fair-ai-public-license to ensure derivative works remain open source.

IV. Disclaimer

Generated models may produce unexpected or harmful outputs. Users must assume all risks and potential consequences of usage.