Vinh H. Pham

Results 17 comments of Vinh H. Pham

@shairoz-deci Yes, the one in this repo is broken. You should clone from the [original DCN](https://github.com/CharlesShang/DCNv2) and install it instead Please reference [this Colab Notebook](https://colab.research.google.com/github/tugstugi/dl-colab-notebooks/blob/master/notebooks/CenterNet_ObjectsAsPoints.ipynb)

Update SDXL result guidance scale: 14.0 static ![sdxl_org](https://github.com/huggingface/diffusers/assets/23548268/d1316ee7-21b6-4076-94a6-728f87581e20) linear ![sdxl_org_linear](https://github.com/huggingface/diffusers/assets/23548268/4ed8dccc-5472-499f-8aee-11124937632c)

It seems like the code to train IP-Adapter is provided in the original repo: https://github.com/tencent-ailab/IP-Adapter

@yiyixuxu yes it does. As @fabiorigano suggested, we could utilize `IPAdapterPlusImageProjectionBlock` however weight loading also need to be updated

So should we convert this project into a diffusers `Pipeline` @sayakpaul? Although the author already uses diffuser component, we would still need some refactoring for ease of use

Hi @a-r-r-o-w , thank you for the good work. I also think 1000 images is small to achieve good result. I would suggest using a larger dataset like [CC12m](https://github.com/google-research-datasets/conceptual-12m). Besides,...

Unfortunately, I also intented to work on this if possible