Update README.md

README.md

@@ -150,5 +150,36 @@ vae = AutoencoderKL.from_single_file(
 It's trickier if the VAE is in [CivitAI](civitai.com), because you can't use
 `from_single_file()` method. It only works for files inside HuggingFace and local files only. You can upload the VAE from there into
 HuggingFace, but you must comply with the model's license before continuing. To solve this issue, you may
-use `wget` or `curl` command to get the file from outside HuggingFace. (To be continued)
+use `wget` or `curl` command to get the file from outside HuggingFace.
+
+Before downloading, to organize the VAE file you want to use and download, change
+the directory to save the downloaded model with `cd`
+and use `-O` option before specifying the file's link and name. It's the same thing
+for both `wget` and `curl`. 
+```py
+# For 'wget'
+!cd <path>; wget -O [filename.safetensors] <link>
+
+# For 'curl'
+!cd <path>; curl -O [filename.safetensors] <link>
+
+# Use only one of them. Replace "filename" with any
+# name you want. If you run the code in Command Prompt or
+# Windows Shell, you don't need the exclamation mark (!).
+```
+
+Since the file is now in your local directory, you can
+finally use `from_single_file()` method normally. Make sure to
+input the correct path for your VAE file. Load the VAE file into [AutoencoderKL](https://huggingface.co/docs/diffusers/en/api/models/autoencoderkl).
+```py
+path = "path to VAE" # Ends with .safetensors file format.
+model = "IDK-ab0ut/Yiffymix_v51"
+vae = AutoencoderKL.from_single_file(path).to("cuda")
+pipeline = StableDiffusionXLPipeline.from_pretrained(
+           model, vae=vae).to("cuda")
+
+# Use 'torch_dtype=torch.float16' for both
+# AutoencoderKL and SDXL pipeline for FP16.
+```
+
 # That's all for this repository. Thank you for reading my silly note. Have a nice day!