Raelina/Raehoshi-illust-XL

Raehoshi illust XL

Overview

Introducing Raehoshi illust XL , an enhanced iteration built upon the Illustrious XL v0.1 model. It aims to elevate the visual style by addressing some of the limitations in the original, such as oversaturation and artifact noise. While these issues are not entirely eliminated, noticeable improvements have been made, and further refinements will continue. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.

Model Details

• Developed by: Raelina
• Model type: Diffusion-based text-to-image generative model
• Model prompt style: Booru-tags
• License: Fair AI Public License 1.0-SD
• Finetuned from: Illustrious XL v0.1

Recommended settings

• Positive prompts:

masterpiece, best quality, good quality,

• Negative prompts:

lowres, (bad quality, worst quality:1.2), bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, signature, watermark,

• CFG: 7
• Sampling steps: 28
• Sampler: Euler a
• Supported Resolution:

1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536

Hires.fix Setting

• Upscaler: 4x_NMKD-YandereNeoXL
• Hires step: 10-15
• Denoising: 0.1-0.3 or 0.55 for latent upscaler

Training config

The model was developed using a two-stage fine-tuning process. In Stage 1, new series and characters were introduced into the model. Stage 2 focused on fixing issues and enhancing the overall style for improved output.

Stage 1

• Dataset : 31k
• Hardware : 2x A100 80gb
• Batch size : 32
• Gradient accumulation steps : 2
• Learning rate : 6e-6
• Text encoder : 3e-6
• Epoch : 15

Stage 2

• Dataset : 2.5k
• Hardware : 1x A100 80gb
• Batch size : 48
• Gradient accumulation steps : 1
• Learning rate : 3e-6
• Text encoder : disable
• Epoch : 15

License

Fair AI Public License 1.0-SD