envs

app.py

@@ -339,7 +339,7 @@ class ImageConductor:
         trajs_video = vis_flow_to_video(controlnet_flows, num_frames=self.model_length) # T-1 x H x W x 3
         torchvision.io.write_video(f'{output_dir}/control_flows/sample-{id}-train_flow.mp4', trajs_video, fps=8, video_codec='h264', options={'crf': '10'})
         controlnet_flows = torch.from_numpy(controlnet_flows)[None][:, :self.model_length, ...]
-        controlnet_flows =  rearrange(controlnet_flows, "b f h w c-> b c f h w").to(device)
+        controlnet_flows =  rearrange(controlnet_flows, "b f h w c-> b c f h w").float().to(device)
 
         dreambooth_model_path = DREAM_BOOTH.get(personalized, '')
         lora_model_path = LORA.get(personalized, '')

pipelines/pipeline_imagecoductor.py

@@ -464,7 +464,7 @@ class ImageConductorPipeline(DiffusionPipeline):
                     print("t", t.device)
                     
                     
-                    
+                    print("self.image_controlnet", self.image_controlnet.controlnet_mid_block.weight.device)
                     
                     img_down_block_additional_residuals, img_mid_block_additional_residuals = self.image_controlnet(
                                 controlnet_noisy_latents, t,