Takamichi Style版本v2.0 SD1.5 (Strong) (Strong)

If you like my content consider supporting me! ?

1 Cookie = Early access to future releases! ?❤️

Locon trained on the style of Takamichi for Pony Diffusion v6 XL based models.

I wasn't entirely satisfied with v1.0 and remade it from scratch.

Pony version

• V2

  • No trigger word and weight 0.8~1.0. Sample images uses weight 1.0.

• V1

  • No trigger word and weight 0.8~1.0. Sample images uses a weight of 0.8.

SD 1.5 version

• V2 Stable (early epoch)

  • No trigger word and weight 1.0. Sample images uses weight 1.0.

• V2 Strong (later epoch)

  • No trigger word and weight 0.8~1.0. Hires.fix or Adetailer is required! You may play with lora block weights for better performance. Sample images uses weight 1.0 and 2x Hires.fix!

• V1 (deprecated)

  • All sample images uses a weight of 0.6 and no trigger word. They were generated at 640x960 with 2x hires. fix.

Disclamer

All the models that I have developed and published on this platform are for entertainment purposes only. They are derived from the base Stable Diffusion model, which means it also includes its inherent issues, limitations and unfiltered capabilities. With that in mind, I am in no way responsible for any content that the user creates with malicious intent while using any of these models. The user assumes complete responsibility for the misuse of these tools and any unethical content created with them. This disclaimer is subject to the laws of the United States of America and the state of California. I reserve the right to remove or report any content that violates the terms of service, ethical standards, or applicable laws.

License conditions

Takamichi Style for Pony Diffusion v6 XL and Stable Diffusion 1.5 © 2024 by Pettan Koutei is licensed under Attribution-NonCommercial-ShareAlike 4.0 International

描述:

Reworked the dataset and training parameters. 110 images and 19800 steps.

? Training Parameters:

• Base Model: NAI

• Training Resolution: 512,768

• Training Batch Size: 2

• Type: LoCon

• DIM / Alpha: 64 / 32

• Conv Dim / Alpha: 24 / 6

• Train On: Unet + TE

• Optimizer: AdamW8bit

• Scheduler: Cosine w/ restarts

• Min SNR Gamma: 8

• Bucket Resolution: 256 - 3072

• Bucket Steps: 64

• Noise Offset: Normal (0.035)

• Image Count: 110

• Epochs: 18

• Repeats: 10

训练词语: