schananas/grounded_sam 🖼️📝🔢 → 🖼️

▶️ 872.2K runs 📅 Oct 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
image-segmentation text-driven-segmentation

About

Mask prompting based on Grounding DINO & Segment Anything | Integral cog of doiwear.it

Example Output

Output

Example outputExample outputExample outputExample output

Performance Metrics

4.40s Prediction Time
4.37s Total Time
All Input Parameters 
{
  "image": "https://st.mngbcn.com/rcs/pics/static/T5/fotos/outfit/S20/57034757_56-99999999_01.jpg",
  "mask_prompt": "clothes,shoes",
  "adjustment_factor": -15,
  "negative_mask_prompt": "pants"
}
Input Parameters
image Type: stringDefault: https://st.mngbcn.com/rcs/pics/static/T5/fotos/outfit/S20/57034757_56-99999999_01.jpg
Image
mask_prompt Type: stringDefault: clothes,shoes
Positive mask prompt
adjustment_factor Type: integerDefault: 0
Mask Adjustment Factor (-ve for erosion, +ve for dilation)
negative_mask_prompt Type: stringDefault: pants
Negative mask prompt
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
Running prediction: 5e05d41d-328d-4e22-ad68-2a09865104b4...
Done!
Version Details
Version ID
ee871c19efb1941f55f66a3d7d960428c8a5afcb77449547fe8e5a3ab9ebc21c
Version Created
October 27, 2023
Run on Replicate →