Suhail

Is it possible to do this without going from GPU -> CPU -> GPU? Code: ```py vis_images = [self.vis_processors["eval"](Image.fromarray(image.cpu().numpy())).unsqueeze(0).to('cuda').squeeze(0) for image in images] features_image = self.blip2_model.extract_features({"image": torch.stack(vis_images)}, mode="image") ``` extract_features...

Different results between AITemplate example and DreamStudio for SD 2.0

2

Using a DDIM scheduler, I get different results:  Is anyone else getting predictable results with the same seed/scheduler? It makes me think there's a...

TypeError: forward() got an unexpected keyword argument 'controlnet_hint'

4

It looks like something has changed with diffusers and it doesn't have this param:   ![CleanShot 2023-03-05 at 12...