nodes/wTechArtist-ComfyUI_VVL_VideoCamera_Advanced
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Jianyuan Wang
2025-03-19 01:35:29 +00:00
committed by GitHub
parent a5ffa7e00a
commit ee7c20a03f
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -3
View File
@@ -58,9 +58,10 @@ model = VGGT.from_pretrained("facebook/VGGT-1B").to(device)
image_names = ["path/to/imageA.png", "path/to/imageB.png", "path/to/imageC.png"]
images = load_and_preprocess_images(image_names).to(device)
with torch.no_grad() and torch.cuda.amp.autocast(dtype=dtype):
# Predict attributes including cameras, depth maps, and point maps.
predictions = model(images)
with torch.no_grad():
with torch.cuda.amp.autocast(dtype=dtype):
# Predict attributes including cameras, depth maps, and point maps.
predictions = model(images)
```
The model weights will be automatically downloaded from Hugging Face. If you encounter issues such as slow loading, you can manually download them [here](https://huggingface.co/facebook/VGGT-1B/blob/main/model.pt) and load, or: