OeAi - illustrious XL
Back

OeAi - illustrious XL
4 1 25

Illustration

2D

unknown

OeAi - illustrious XL

OeAi   A Fine-tuned Model Based on illustrious XL 1.1

  • Fine-tune illustrious XL 1.1 to lean more toward a flat, light-colored style
  • Even without using any danbooru-style prompts, it performs well in image generation
  • Add artist names in the style of the danbooru tag set to replicate styles
  • You can use it like NAI and train it as a base model
  • Using danbooru tag set prompts achieves better results compared to illustrious XL 1.1 (better anime illustration style)
  • Regarding image generation capabilities: This model still performs well when generating high-resolution images, so it does not require second sampling (original resolution supports 1536x1536; you can check my sample images, which all include comfyui workflow information)
  • Parameters: Sampling steps: 26 CFG: 7 Sampler: euler_ancestral Schedule: ddim_uniform Resolutions: 1536x1536, 1536x2112, 1472x2240, 1664x1984 (for generating horizontal images, it is recommended to reverse the width and height resolutions)

This is a stunning new illustration model that you can use to create amazing images. It still supports input of the danbooru tag set and is fine-tuned based on OeAi v1.0. The settings and Lora models from version v1.0 are still compatible with this model.

This model is sourced from an external transfer (transfer address: https://www.liblib.art/modelinfo/b0865a5ae56947e4871e0d0b0d866dba?from=search&versionUuid=53991c887d6d4f228ff32a0571cbc45f ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request

Tfeed

Tfeed

Illustration

2D

unknown

Model Information

Frozen
Original author：
Anlia
Model Type：
Checkpoint
Basic Model：
SDXL 1.0
Resource Name：
models/checkpoints/oeaiIllustriousXLMore_oeaiV12UE.safetensors
MD5：
53b8411d89e3e7d503016c0d135019af

OeAi   A Fine-tuned Model Based on illustrious XL 1.1

  • Fine-tune illustrious XL 1.1 to lean more toward a flat, light-colored style
  • Even without using any danbooru-style prompts, it performs well in image generation
  • Add artist names in the style of the danbooru tag set to replicate styles
  • You can use it like NAI and train it as a base model
  • Using danbooru tag set prompts achieves better results compared to illustrious XL 1.1 (better anime illustration style)
  • Regarding image generation capabilities: This model still performs well when generating high-resolution images, so it does not require second sampling (original resolution supports 1536x1536; you can check my sample images, which all include comfyui workflow information)
  • Parameters: Sampling steps: 26 CFG: 7 Sampler: euler_ancestral Schedule: ddim_uniform Resolutions: 1536x1536, 1536x2112, 1472x2240, 1664x1984 (for generating horizontal images, it is recommended to reverse the width and height resolutions)

This is a stunning new illustration model that you can use to create amazing images. It still supports input of the danbooru tag set and is fine-tuned based on OeAi v1.0. The settings and Lora models from version v1.0 are still compatible with this model.

This model is sourced from an external transfer (transfer address: https://www.liblib.art/modelinfo/b0865a5ae56947e4871e0d0b0d866dba?from=search&versionUuid=53991c887d6d4f228ff32a0571cbc45f ）,if the original author has objections to this transfer, you can click，
Appeal
We will, within 24 hours, edit, delete, or transfer the model to the original author according to the original author's request