add requirements

app.py

@@ -9,6 +9,7 @@ import os
 
 hf_hub_download('wondervictor/ControlAR', filename='canny_MR.safetensors', cache_dir='./checkpoints/')
 hf_hub_download('wondervictor/ControlAR', filename='depth_MR.safetensors', cache_dir='./checkpoints/')
+hf_hub_download('google/flan-t5-xl', cache_dir='./checkpoints/')
 
 
 DESCRIPTION = "# [ControlAR: Controllable Image Generation with Autoregressive Models](https://arxiv.org/abs/2410.02705) \n ### The first row in outputs is the input image and condition. The second row is the images generated by ControlAR.  \n ### You can run locally by following the instruction on our [Github Repo](https://github.com/hustvl/ControlAR)."

model.py

@@ -84,8 +84,8 @@ class Model:
         t5_model = T5Embedder(
             device=self.device,
             local_cache=True,
-            cache_dir='checkpoints/t5-ckpt',
-            dir_or_name='google/flan-t5-xl',
+            cache_dir='checkpoints/flan-t5-xl',
+            dir_or_name='flan-t5-xl',
             torch_dtype=precision,
             model_max_length=120,
         )