README.md: tweaks

README.md

@@ -58,7 +58,7 @@ It's a prerequisite for a number of object manipulation tasks like:
 - Replace an object in an image
 - ...
 
-Out-of-the box, the Finegrain Object Cutter requires a bounding box as an input, but you can easily augment it to enable "prompt to select object" scenarios - see the Finegrain Object Cutter Hugging Face space for an example implementation.
+Out-of-the box, the Finegrain Box Segmenter requires a bounding box as an input, but you can easily augment it to enable "prompt to select object" scenarios - see the [Finegrain Object Cutter Hugging Face space](https://huggingface.co/spaces/finegrain/finegrain-object-cutter) for an example implementation.
 
 ## Training
 
@@ -85,7 +85,7 @@ Given our focus on e-commerce, we crafted a specific test set, and in order to e
 
 We're using the usual metrics, namely MAE, Smeasure, Emeasure and Dice, computed with [PySODMetrics](https://github.com/lartpang/PySODMetrics). We'll add more later to account for matting aspects (transparent objects) - still a work-in-progress on our end.
 
-| Model | **MAE** ↓ | **Smeasure** ↑ | **Smeasure** ↑ | **Dice** ↑ |
+| Model | **MAE** ↓ | **Smeasure** ↑ | **Emeasure** ↑ | **Dice** ↑ |
 |--|--|--|--|--|
 | `briaai/RMBG-1.4` (x) | 0.0226 | 90.7% | 94.3% | 88.5% |
 | `ZhengPeng7/BiRefNet` (xx) | 0.0194 | 93.1% | 95.1% | 91.5% |
@@ -172,7 +172,7 @@ mask = segmenter(input_image, box_prompt=(24, 133, 588, 531))
 mask.save("output.png")
 ```
 
-### With Comfy UI
+### With ComfyUI (https://registry.comfy.org/publishers/finegrain/nodes/comfyui-refiners)
 
 Install the `comfyui-refiners` custom nodes:
 ```