diff --git a/README.md b/README.md
index fd709cf..bc1b4a3 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,8 @@ ComfyUI nodes for outpainting images with diffusers, based on [diffusers-image-o
   | 	merges.txt, special_tokens_map.json, tokenizer_config.json, vocab.json	| |
   
 ## Overview
-**Minimum VRAM**: 6 gb with 1280x720 image, rtx 3060, RealVisXL_V5.0_Lightning, sdxl-vae-fp16-fix, controlnet-union-sdxl-promax using `sequential_cpu_offload`, otherwise 8,3 gb.
+- **Minimum VRAM**: 6 gb with 1280x720 image, rtx 3060, RealVisXL_V5.0_Lightning, sdxl-vae-fp16-fix, controlnet-union-sdxl-promax using `sequential_cpu_offload`, otherwise 8,3 gb;
+- As seen in [this issue](https://github.com/GiusTex/ComfyUI-DiffusersImageOutpaint/issues/7#issuecomment-2410852908), images with **square corners** are required.
 
 The extension gives 4 nodes:
 - **Load Diffusion Outpaint Models**: a simple node to load diffusion `models`. You can download them from Huggingface (the extension doesn't download them automatically);