Image-Text-to-Text
sam2
ONNX
Safetensors
comfyui
wevisone-vl
mask2alpha
ocr
image-matting
segmentation
Instructions to use t8star/WeVisOne-VL-Comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sam2
How to use t8star/WeVisOne-VL-Comfy with sam2:
# Use SAM2 with images import torch from sam2.sam2_image_predictor import SAM2ImagePredictor predictor = SAM2ImagePredictor.from_pretrained("t8star/WeVisOne-VL-Comfy") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): predictor.set_image(<your_image>) masks, _, _ = predictor.predict(<input_prompts>)# Use SAM2 with videos import torch from sam2.sam2_video_predictor import SAM2VideoPredictor predictor = SAM2VideoPredictor.from_pretrained("t8star/WeVisOne-VL-Comfy") with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16): state = predictor.init_state(<your_video>) # add new prompts and instantly get the output on the same frame frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>) # propagate the prompts to get masklets throughout the video for frame_idx, object_ids, masks in predictor.propagate_in_video(state): ... - Notebooks
- Google Colab
- Kaggle
Download mask2alpha_head.validation.json from t8star/WeVisOne-VL-Comfy: direct link, hf CLI and curl.
- Browser
- Download file 365 Bytes
-
https://huggingface.co/t8star/WeVisOne-VL-Comfy/resolve/main/mask2alpha_head.validation.json
- Command line
-
hf download hf://t8star/WeVisOne-VL-Comfy/mask2alpha_head.validation.json
-
curl -L -o mask2alpha_head.validation.json https://huggingface.co/t8star/WeVisOne-VL-Comfy/resolve/main/mask2alpha_head.validation.json
365 Bytes
| { | |
| "head_checkpoint_sha256": "bac23dd096037cf1ce161e0c9546af326cd3cfffa6da647864da6e4f79268a05", | |
| "onnx_sha256": "5595195c7e968c9764489fa37f7a0a2d937db015902b887e34299d11cec96ae7", | |
| "onnx": "mask2alpha_head.onnx", | |
| "max_error": 1.0609626770019531e-05, | |
| "mean_error": 4.0331337913812604e-07, | |
| "fixed_shape": [ | |
| 1, | |
| 3, | |
| 1024, | |
| 1024 | |
| ] | |
| } |