envs

app.py

@@ -238,8 +238,8 @@ 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")
-        text_encoder = CLIPTextModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="text_encoder")
-        vae          = AutoencoderKL.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="vae")
+        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")
         unet = UNet3DConditionFlowModel.from_pretrained_2d("models/sd1-5/", unet_additional_kwargs=OmegaConf.to_container(inference_config.unet_additional_kwargs))