Update README.md

README.md

@@ -7,27 +7,42 @@ tags:
 - natsuki
 ---
 
-SD 1.5 dreambooth models trained on Anythingv3. Checkpoint files trained on (number of steps divided by 90) images, on AnythingV3. Focused on checkpoints before moving on to safetensors and lora (using loras with checkpoints and even TIs can bring out most accurate results).
+SD 1.5 dreambooth models trained 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.
+Lora also trained on Anythingv3.
+
+Textual inversion embedding versions can be found [here](https://huggingface.co/922-CA/gfl-ddlc-TI-tests) (trained off the same or similar datasets).
 
 # yr1-2430 (~12/2022)
 * Keyword: yrg
-* WIP
+* First attempt
+
+# yr2/3 (~12/2022) [TBA]
+* Keyword: yrg
+* Further attempts
 
 # sa1-1800 (~12/2022)
 * Keyword: syr
-* WIP
+* First attempt
 
+# sa2 (~12/2022) [TBA]
+* Keyword: syr
+* Further attempts
+
+# na1 (~12/2022) [TBA]
+* Keyword: ntsk
+* First attempt
+  
 # na2-2160 (~12/2022)
 * Keyword: ntsk
-* WIP
+* Second attempt
   
 # na3a-1800 (~12/2022)
 * Keyword: ntsk
-* WIP
+* Third attempt
 
 # ml6-10 (~05/2023)
-* WIP
+* Keyword: monika \(doki doki literature club\)
+* Tenth version
 
-MTBA
+MTBA (previews, any future loras or models trained off better bases- hopefully some SDXL too)