Updated FAQ (markdown)

FAQ.md

@@ -38,6 +38,21 @@ You can try forcing plain text auth creds storage by removing line with "credSto
 
 You have to use one of AWS's GPU-enabled VMs and their Deep Learning OS images. These have the right divers, the toolkit and all the rest already installed and optimized. [#70](https://github.com/AbdBarho/stable-diffusion-webui-docker/issues/70)
 
+---
+### lstein: OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'
+
+Just update `docker-compose.yaml` to [refresh the models](https://github.com/lstein/stable-diffusion/issues/34) (i.e. `PRELOAD=true`). [#72](https://github.com/AbdBarho/stable-diffusion-webui-docker/issues/72#issuecomment-1250382056)
+
+```yml
+  lstein:
+    <<: *base_service
+    profiles: ["lstein"]
+    build: ./services/lstein/
+    environment:
+      - PRELOAD=true
+      - CLI_ARGS=
+```
+
 ---
 
 ### Output is a always green image