Zeqiang Lai

See my implementation, https://github.com/Zeqiang-Lai/DragGAN Have fun with it.

> [Zeqiang-Lai/DragGAN@70638b0](https://github.com/Zeqiang-Lai/DragGAN/commit/70638b0a688d1860fe9245d176fd91d765c4c01d) > > Name changed from DragDiffusion to DragGAN 1 hour ago to hijack the popularity - That's just low. We have no intention on hijacking anything, changed it...

> @cientgu @zzctan > > Could I have some help parsing q_posterior? > > https://github.com/microsoft/VQ-Diffusion/blob/3c98e77f721db7c787b76304fa2c96a36c7b00af/image_synthesis/modeling/transformers/diffusion_transformer.py#L235-L267 > > I believe it's computing equation 11 in log space, but I still have...

See also [Anything2Image](https://github.com/Zeqiang-Lai/Anything2Image) and [InternGPT](https://github.com/OpenGVLab/InternGPT), it is implemented with Diffusers.

> I'm rather new to diffusion, but does Imagebind provide any sort of decoder? I thought it was just training an encoder, and if that's the case how are these...

Is there any progress in releasing smaller models?

I am very confused about the conversation templates of llava-v1.5 as well(pretraining, fine-tuning, and inference use three different templates), @haotian-liu would appreciate for the response. > I have a similar...

Take a look of my implementation, https://github.com/Zeqiang-Lai/DragGAN

Take a look of my implementation, https://github.com/Zeqiang-Lai/DragGAN

Due to the limitation of GAN inversion, it is possible that your custom images are distorted. Besides, it is also possible the manipulations fail due to the limitation of our...