Adding v1b embeds

README.md

@@ -1,12 +1,11 @@
 ---
-language: 
+language:
   - en
 tags:
-- cyberpunk
-- anime
-- stable-diffusion
-- rebecca
-
+  - cyberpunk
+  - anime
+  - stable-diffusion
+  - rebecca
 ---
 
 # REBECCA
@@ -25,13 +24,21 @@ _Shameless plug: If you want a *free open source* fully local booru alternative,
 
 [Trained via this GUI](https://github.com/n00mkrad/text2image-gui), but note that it's quite restrictive in training options.
 
-- **rebecca-71a-v1**: Trained with "very high quality" preset and "normal" learning rate. [Examples](https://imgur.com/a/kmcS2Ve)
+- **rebecca-71a-v1**: Trained with "very high quality" preset and "normal" learning rate.
+  - [Examples](https://imgur.com/a/kmcS2Ve)
 
 ## EMBEDDINGS
 
 _Note: You'll have to rename your chosen embedding to "rebecca"_
 
-- **rebecca-71a-v1-embeddings**: Embedding trained with voldy's web-ui with 8 tokens per vector, using a learning rate of _0.02:200, 0.01:1000, 0.005:2000, 0.002:3000, 0.0005:4000, 0.00005_, for 20k steps. [Examples with the 20k embed](https://imgur.com/a/j0u1FlO)
+- **rebecca-71a-v1-embeddings**: Embedding trained with voldy's web-ui with 8 tokens per vector, using a learning rate of _0.02:200, 0.01:1000, 0.005:2000, 0.002:3000, 0.0005:4000, 0.00005_, for 20k steps.
+  - [Examples with the 20k embed](https://imgur.com/a/j0u1FlO)
+- **rebecca-71a-v1b-embeddings**: Embedding trained with voldy's web-ui with 8 tokens per vector, using a learning rate of _0.005_, for 30k steps.
+  - [Examples with the 5k embed](https://imgur.com/a/MAlHx3d)
+  - [Examples with the 10k embed](https://imgur.com/a/SeGNh31)
+  - [Examples with the 15k embed](https://imgur.com/a/sIpkyQ9)
+  - [Examples with the 20k embed](https://imgur.com/a/IHsAj9j)
+  - [Examples with the 30k embed](https://imgur.com/a/qF4sZQe)
 
 ## HYPERNETWORKS