metadata

license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
pipeline_tag: text-to-image
base_model:
  - OnomaAIResearch/Illustrious-xl-early-release-v0
tags:
  - stable-diffusion
  - stable-diffusion-xl

Illumina-XL-1.0

Modified Illustrious-XL-v0.1

Prompt Guidelines

Almost same as the base model

Recommended Prompt

None(Works good without masterpiece, best quality)

Recommended Negative Prompt

worst quality, low quality, bad quality, lowres, jpeg artifacts, unfinished

Recommended Settings

Steps: 14-28

Sampler: DPM++ 2M(dpmpp_2m)

Scheduler: Simple or Karras

Guidance Scale: 4-9

Hires.fix

Hires upscaler: 4x-UltraSharp or Latent

Denoising strength: 0.3-0.4(0.6 for latent)

Merge recipe(Weighted sum)

I made 5 Illustrious-based models and merged them.

Ill-based finetuned model C * 0.65 + Ill-based finetuned model D * 0.35 = tmp1
tmp1 * 0.8 + Ill-based finetuned B * 0.2 = tmp2
tmp2 * 0.7 + Ill-based finetuned E * 0.3 = tmp3
tmp3 * 0.7 + Ill-based finetuned A * 0.3 = Illumina-XL-1.0

Training scripts:

sd-scripts

Notice

This model is licensed under Fair AI Public License 1.0-SD

If you make modify this model, you must share both your changes and the original license.

You are prohibited from monetizing any close-sourced fine-tuned / merged model, which disallows the public from accessing the model's source code / weights and its usages.