chavinlo

> @midihex I think you have the right idea here and it needs to be flushed out more, I am putting together a community effort to continue where this work...

Furthermore, one user already got the training code working. I will try to contact him and if he denies I will try it my self

continuing the conversation we had on discord, would `torch.cuda.empty_cache()` be called inside the inference function?

done

Not official but https://github.com/chavinlo/riffusion-manipulation

Hi Jonny and yes I am also interested

I can provide you with some GPU compute if needed Either distributed (https://github.com/chavinlo/distributed-diffusion one of my side projects) Or local (A100s) but only for a while

Any updates? Really interested in this.

https://wandb.ai/peruano/huggingface/runs/ei57qbzm/overview?workspace=user-peruano

> Can I know how you run the model to generate images? late, but there are many repositories that just replace CLIP for ImageBind A good example is https://github.com/Birch-san/imagebind-guided-diffusion