IDKiro
/

sdxs-512-0.9

StableDiffusionPipeline

stable-diffusion

Model card Files Files and versions Community

IDKiro commited on Mar 27

Commit

00430b9

•

1 Parent(s): 9d3f101

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ Model Information:
 - VAE: [TAESD](https://huggingface.co/madebyollin/taesd)
 The main differences between this model and version 1.0 are in three aspects:
-1. This version employs TAESD, which may produce low-quality images when weight_type is float16. Our image decoder is not compatible with the current version of diffusers, so it will not be provided now..
 2. This version did not perform the LoRA-GAN finetune mentioned in the implementation details section, which may result in slightly inferior image details.
 3. This version replaces self-attention with cross-attention in the highest resolution stages, which introduces minimal overhead compared to directly removing all Transformer layers.

 - VAE: [TAESD](https://huggingface.co/madebyollin/taesd)
 The main differences between this model and version 1.0 are in three aspects:
+1. This version employs TAESD, which may produce low-quality images when weight_type is float16. Our image decoder is not compatible with the current version of diffusers, so it will not be provided now.
 2. This version did not perform the LoRA-GAN finetune mentioned in the implementation details section, which may result in slightly inferior image details.
 3. This version replaces self-attention with cross-attention in the highest resolution stages, which introduces minimal overhead compared to directly removing all Transformer layers.