SD 1.5 dreambooth models fine-tuned on Anythingv3. Checkpoint files trained on (number of steps divided by 90) images scraped from boorus, with text encoder trained for around (number of images times 12) steps. Focused on ckpts before moving on to safetensors and lora. (using loras with checkpoints and even TIs can bring out most accurate results).

Lora also trained on Anythingv3.

Textual inversion embedding versions can be found here (trained off the same or similar datasets).

yr1-2430 (12/05/2022)

• Keyword: yrg
• First attempt

yr5 (12/08/2022)

• Keyword: yrg
• Second version

sa1-1800 (12/08/2022)

• Keyword: syr
• First attempt

sa2 (12/08/2022)

• Keyword: syr
• Second attempt

na1-1800 (12/06/2022)

• Keyword: ntsk
• First attempt

na2-2160 (12/07/2022)

• Keyword: ntsk
• Second attempt

na3a-1800 (12/07/2022)

• Keyword: ntsk
• Third attempt

ml6-10 (~05/2023)

• Keyword: monika (doki doki literature club)
• Tenth version
• Previews (Silicon29 and BreakDomain Anime)

MTBA (previews, any future loras or models trained off better bases- hopefully some SDXL too)