abydos-xl-1.1

Abydos-XL-1.1

Modified Illustrious-XL-v0.1 with Blue Archive style

This is the next version of Abydos-XL-1.0, Slightly improved background(scenery), stability and detail rendering.

You can find example images on Civitai model page

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, abstract, oldest, photoshop \(medium\)

To improve the quality of background, add simple background, transparent background to Negative Prompt.

Recommended Settings

Steps: 14-28

Sampler: DPM++ 2M(dpmpp_2m)

Scheduler: Simple

Guidance Scale: 4-9

Hires.fix

Upscaler: 4x-UltraSharp or Latent

Denoising strength: 0.5(0.6 for latent)

Training information

Finetuned Illumina-XL-1.1 by repeating the training and merging a DoRA 6 times with sd-scripts.

• Network module: lycoris_kohya(algo=lora, dora_wd=True)
• Resolution: 1024(Bucketing enabled, min 512, max 2048)
• Optimizer: Lion
• Train U-Net only: Yes
• LR Scheduler: cosine with restart(warmup ratio=0.1, repeat=4-6)
• Learning Rate: various(min=1e-05, max=6e-05)
• Noise Offset: 0.04
• Immiscible Noise: 2048
• Batch size: 1
• Gradient Accumulation steps: 1
• Dim/Alpha: 16/4
• Conv Dim/Alpha: 1/0.25

Dataset information

Dataset size: 289

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.