Ahsen Khaliq

@bes-dev great, but i dont think streamlit works in colab notebook like gradio does, we also support queueing and concurrency requests

dreambooth training script was merged to diffusers https://github.com/huggingface/diffusers/tree/main/examples/dreambooth

colab for training dreambooth with diffusers is out: https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb, includes a gradio web ui, from the gradio side it can be added to this web ui but would be easier...

@betterze could anycost gan help with this https://github.com/mit-han-lab/anycost-gan

this might be related to setting a default image using gr.Image(value="image.png"), after removing that works on the images shown above

@abhigoku10 Hi check out yolov5 gradio hub: https://gradio.app/hub/AK391/yolov5 repo: https://github.com/AK391/yolov5/blob/master/utils/gradio/demo.py is that similar to what you are looking to do?

@abhigoku10 yes you can load a custom model as well without using torch hub see this example https://github.com/AK391/vits/blob/main/gradiodemo.py

@abhigoku10 1. there is a image editor, can access by clicking edit in the image component area to draw lines on the image 2. Not sure about this, can you...

@abhigoku10 regarding 6. see https://github.com/gradio-app/gradio/issues/236 optional input components are in the works currently user would have to populate both the fields for the front end to respond One option could...

@abhigoku10 for 1. not sure will look into it 2. see https://gradio.app/docs, css (str) - custom css or path to custom css file to use with interface. 3. do you...