Update README.md

README.md

@@ -11,7 +11,8 @@ language:
 
 # Info
 
-A quick and dirty [NAFNet](https://github.com/megvii-research/nafnet)-small based image restoration model for Qwen/Wan VAE grid artifact removal/mitigation, trained with 0 experience and a lot of AI handholding.
+A quick and dirty [NAFNet](https://github.com/megvii-research/nafnet)-small based image restoration model for Qwen/Wan VAE grid artifact removal/mitigation, trained with 0 experience and a lot of AI handholding.  
+(Not trained for Qwen 2.1/Wan 2.2 VAE, doubt it'll work but you tell me)
 
 - **Aim:** Something on par with or hopefully better than Nyquist Notch shader - Remove the grid without changing/deforming/destroying anything
 - **Limitations:** 1. Maybe realism, idk; 2. This model is only trained on what the VAE changes and very likely won't touch any extra noise or such your diffusion model generated
@@ -91,6 +92,6 @@ You can find PyTorch checkpoints as they came from training in the `train/` subf
 - `100k` steps - pretrain
 - `30k` steps - finetune
 
-Training code (i think configs too):
+Training code (configs too, probably):
 
 <https://github.com/DraconicDragon/NAFNet-c>