Update README.md

README.md

@@ -52,7 +52,7 @@ prior_output = prior(
 
 decoder.enable_model_cpu_offload()
 decoder_output = decoder(
-    image_embeddings=prior_output.image_embeddings.to(torch.float16),
+    image_embeddings=prior_output.image_embeddings,
     prompt=prompt,
     negative_prompt=negative_prompt,
     guidance_scale=2.0,
@@ -85,7 +85,7 @@ decoder_output.save("cascade.png")
 ## Dataset:
 
 **GPU used for captioning**: 1x Intel ARC A770 16GB  
-**Model used for captioning**: SmilingWolf|wd-v1-4-convnextv2-tagger-v2  
+**Model used for captioning**: SmilingWolf/wd-v1-4-convnextv2-tagger-v2  
 
 
 | dataset name | total images | total chunk |