Raehoshi illust XL

CHECKPOINT
Reprint


Updated:

Raehoshi Illust XL

an enhanced iteration built upon the Illustrious XL 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. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.

Why Early Access?

Early access helps cover the cost of training and development. By purchasing early access, you're directly supporting the development of my models. If you'd like to support me further, you can also buy me a coffee on Ko-fi! Your support keeps the project going and ensures even better models in the future.

Recommended setting

Positive prompt :

masterpiece, best quality, absurdres

Negative prompt :

lowres, bad quality, worst quality, poorly drawn, multiple views, bad anatomy, bad hands, signature, watermark

Steps : 25-28

CFG : 5-6

Sampler : euler a

Standard resolution :

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

High resolution :

1024 x 1536, 832 x 1536, 1536 x 1024, 1536 x 832, 1536 x 1536

Hires.fix Setting:

Training Details

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 : v1-31k, v2-37k, v3-34k, v4-60k, v5,v5.1-18k

  • Hardware : 2x A100 80gb, v3, v4, v5, v5.1-2x H100 80gb

  • Batch size : 32

  • Gradient accumulation steps : 2

  • Learning rate : 6e-6

  • Text encoder : 3e-6

  • Epoch : 15

Stage 2

  • Dataset : v1-2.5k, v2 and v3-2.3k, v4-2.5k, v5-2k, v5.1-1.8k

  • Hardware : 1x A100 80gb

  • Batch size : 48

  • Gradient accumulation steps : 1

  • Learning rate : 3e-6, v5.1-2.5e-6

  • Text encoder : disable

  • Epoch : 15

List of New Series/Characters Trained:

  • Zenless zone zero character up to 2.0

  • Wuthering waves character up to 2.4

  • HSR character up to 3.4

  • Genshin character up to 5.7

  • Dandadan

  • Make heroine ga oo sugiru

  • Kusuriya no Hotorigoto

  • Hololive from justice and dev is

  • Indie Vtuber dooby and yuuki Sakuna

  • 100 girlfriends who really love you

  • Haite kudasai takamine-san

  • Alina clover

For character prompts, please refer to the Danbooru site for accurate tags and references.

License

Since each version uses a different base, the license for each version will also be different v1, v2, v2.1 based on Illustrious v0.1 Fair AI Public License 1.0-SD

v3 based on NoobAI Fair AI Public License 1.0-SD with Addition No Commercial allowed

v4 and v5.1 based on Illustrious v1.1 original SDXL License

v5 based on Illustrious v2.0 original SDXL License

Special thanks to Joe for supporting my works

Special thanks to Juno for supporting my works and help me with early tester

The model already exists. If you are the creator, please contact us to claim it.
View duplicate model

Version Detail

Illustrious
About this version Improve stability Improve anatomy Fix dupe character/body in some generation Improve high resolution generation (see recommended highres in the model detail) Note: Due to some issues in v5, which seem to stem from the Illustrious v2.0 base, this update has been rolled back to v4, which uses the Illustrious 1.1 base, so this version continues training from v4

Project Permissions

Model reprinted from : https://civitai.com/models/846917?modelVersionId=1912640

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts