Update app.py

app.py

@@ -17,14 +17,23 @@ import safetensors.torch
 from safetensors.torch import load_file
 from huggingface_hub import HfFileSystem, ModelCard
 from huggingface_hub import login, hf_hub_download
+hf_token = os.environ.get("HF_TOKEN")
+login(token=hf_token)
 
+cache_path = path.join(path.dirname(path.abspath(__file__)), "models")
+os.environ["TRANSFORMERS_CACHE"] = cache_path
+os.environ["HF_HUB_CACHE"] = cache_path
+os.environ["HF_HOME"] = cache_path
+
+torch.set_float32_matmul_precision("medium")
 
 # Load LoRAs from JSON file
 with open('loras.json', 'r') as f:
     loras = json.load(f)
 
 # Initialize the base model
-dtype = torch.float16
+dtype = torch.bfloat16
+device = "cuda" if torch.cuda.is_available() else "cpu"
 base_model = "AlekseyCalvin/SilverAgePoets_FluxS_TestAlpha_Diffusers"
 pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=dtype).to("cuda")
 #pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=torch.float16).to("cuda")