Spaces:
Running
on
A10G
Running
on
A10G
Commit
•
e6abd00
1
Parent(s):
2a6681f
docs
Browse files
app.py
CHANGED
@@ -284,6 +284,10 @@ def main():
|
|
284 |
"in almost 30 design styles. After fetching all these images, we started adding metadata such as "
|
285 |
"captions (from the BLIP captioning model) and segmentation maps (from the HuggingFace UperNetForSemanticSegmentation model). "
|
286 |
)
|
|
|
|
|
|
|
|
|
287 |
st.write("### About the model")
|
288 |
st.write(
|
289 |
"These were then used to train the controlnet model to generate quality interior design images by using "
|
@@ -306,12 +310,12 @@ def main():
|
|
306 |
"by doing this, the users don't need to make a segmentation map in an external tool. Everything needed can be done within this demo."
|
307 |
)
|
308 |
|
309 |
-
st.write("### News: Fondant - an open source data-centric framework for Foundation model finetuning")
|
310 |
-
st.write("The ML6 team
|
311 |
-
|
312 |
-
|
313 |
-
|
314 |
-
st.write("The framework is build on top of kubeflow pipelines and abstracts all the complexity of efficient storing and moving of large datasets, so you can focus on implemented just that piece of code that you need without worrying about the rest. We also build it to run on each Cloud provider or VM. You can find the code on our github page: https://github.com/ml6team/fondant.")
|
315 |
|
316 |
st.write("### Testing images")
|
317 |
st.write("If you don't have any pictures close, you can use one of these images to test the model:")
|
|
|
284 |
"in almost 30 design styles. After fetching all these images, we started adding metadata such as "
|
285 |
"captions (from the BLIP captioning model) and segmentation maps (from the HuggingFace UperNetForSemanticSegmentation model). "
|
286 |
)
|
287 |
+
st.write("For the gathering and inference of the metadata we used the Fondant framework (https://github.com/ml6team/fondant) made by ML6 (https://www.ml6.eu/), which is an open source "
|
288 |
+
"data centric framework for data preparation. The pipeline used for training this controlnet will soon be available as an "
|
289 |
+
"example pipeline within Fondant and can be easily adapted for building your own dataset."
|
290 |
+
)
|
291 |
st.write("### About the model")
|
292 |
st.write(
|
293 |
"These were then used to train the controlnet model to generate quality interior design images by using "
|
|
|
310 |
"by doing this, the users don't need to make a segmentation map in an external tool. Everything needed can be done within this demo."
|
311 |
)
|
312 |
|
313 |
+
# st.write("### News: Fondant - an open source data-centric framework for Foundation model finetuning")
|
314 |
+
# st.write("The ML6 team is proud to announce that we are open sourcing our Fondant framework, which is a "
|
315 |
+
# "data-centric framework that allows you to prepare large scale multimodal datasets with ease. We have implemented the components "
|
316 |
+
# "that we used to train this controlnet model in Fondant as an example pipeline, and we are excited to see what you can do with it! In the future we will add a whole library of plug-and-play data preparation components, such as different ML models and filtering steps, in addition to dataset scraping components that connect to LAION5B."
|
317 |
+
# )
|
318 |
+
# st.write("The framework is build on top of kubeflow pipelines and abstracts all the complexity of efficient storing and moving of large datasets, so you can focus on implemented just that piece of code that you need without worrying about the rest. We also build it to run on each Cloud provider or VM. You can find the code on our github page: https://github.com/ml6team/fondant.")
|
319 |
|
320 |
st.write("### Testing images")
|
321 |
st.write("If you don't have any pictures close, you can use one of these images to test the model:")
|