Spaces:
Runtime error
Runtime error
update: add Space description
Browse files
app.py
CHANGED
@@ -119,9 +119,13 @@ block = gr.Blocks().queue()
|
|
119 |
|
120 |
with block:
|
121 |
gr.Markdown("""
|
122 |
-
# Color-Canny-
|
123 |
|
124 |
-
This is
|
|
|
|
|
|
|
|
|
125 |
""")
|
126 |
with gr.Row():
|
127 |
with gr.Column():
|
|
|
119 |
|
120 |
with block:
|
121 |
gr.Markdown("""
|
122 |
+
# 🧨 Color-Canny-ControlNet
|
123 |
|
124 |
+
This is an extended model of ControlNet that not only utilizes the Canny edge of images but also incorporates the color features.
|
125 |
+
|
126 |
+
We trained this model on the cleaned laion-art dataset that contains 2.6 million images with 2 epochs, using the Canny edge and color mosaic of the images as input. The processed dataset and pretrained model can be found in [ghoskno/laion-art-en-colorcanny](https://huggingface.co/datasets/ghoskno/laion-art-en-colorcanny) and [ghoskno/Color-Canny-Controlnet-model](https://huggingface.co/ghoskno/Color-Canny-Controlnet-model).
|
127 |
+
|
128 |
+
This allows generated images to maintain the same color composition as the original images. If you are looking to control both the contours and colors of the original image while using ControlNet to generate images, then this is the best option for you! You can try out this model or test the examples provided below 🤗.
|
129 |
""")
|
130 |
with gr.Row():
|
131 |
with gr.Column():
|