envs

app.py

@@ -237,7 +237,7 @@ def points_to_flows(track_points, model_length, height, width):
 class ImageConductor:
     def __init__(self, device, unet_path, image_controlnet_path, flow_controlnet_path, height, width, model_length, lora_rank=64):
         self.device = device
-        tokenizer    = CLIPTokenizer.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="tokenizer")
+        tokenizer    = CLIPTokenizer.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="tokenizer").to(device)
         text_encoder = CLIPTextModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="text_encoder").to(device)
         vae          = AutoencoderKL.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="vae").to(device)
         inference_config = OmegaConf.load("configs/inference/inference.yaml")