dvir-bria commited on
Commit
e75b153
·
verified ·
1 Parent(s): 7b9b17c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -37,7 +37,7 @@ Join our [Discord community](https://discord.gg/Nxe9YW9zHS) for more information
37
 
38
  # What's New
39
 
40
- BRIA 2.3 ControlNet Generative Fill can be applied on top of BRIA 2.3 Text-to-Image and therefore enable to use [Fast-LORA](https://huggingface.co/briaai/BRIA-2.3-FAST-LORA). This results in extremely fast inpainting model, requires only 1.6s using A10 GPU.
41
 
42
 
43
 
@@ -108,7 +108,7 @@ def download_image(url):
108
 
109
 
110
  def get_masked_image(image, image_mask, width, height):
111
- image_mask = image_mask # inpaint area is white
112
  image_mask = image_mask.resize((width, height)) # object to remove is white (1)
113
  image_mask_pil = image_mask
114
  image = np.array(image.convert("RGB")).astype(np.float32) / 255.0
 
37
 
38
  # What's New
39
 
40
+ BRIA 2.3 ControlNet Generative Fill can be applied on top of BRIA 2.3 Text-to-Image and therefore enable to use [Fast-LORA](https://huggingface.co/briaai/BRIA-2.3-FAST-LORA). This results in extremely fast generative fill model, requires only 1.6s using A10 GPU.
41
 
42
 
43
 
 
108
 
109
 
110
  def get_masked_image(image, image_mask, width, height):
111
+ image_mask = image_mask # fill area is white
112
  image_mask = image_mask.resize((width, height)) # object to remove is white (1)
113
  image_mask_pil = image_mask
114
  image = np.array(image.convert("RGB")).astype(np.float32) / 255.0