Update app.py

app.py

@@ -30,7 +30,7 @@ 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")
+#torch.set_float32_matmul_precision("medium")
 
 # Load LoRAs from JSON file
 with open('loras.json', 'r') as f:
@@ -38,13 +38,14 @@ with open('loras.json', 'r') as f:
 
 # Initialize the base model
 dtype = torch.bfloat16
-device = "cuda" if torch.cuda.is_available() else "cpu"
 base_model = "AlekseyCalvin/Artsy_Lite_Flux_v1_by_jurdn_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")
 torch.cuda.empty_cache()
 
-clipmodel = 'long'
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+clipmodel = 'norm'
 if clipmodel == "long":
     model_id = "zer0int/LongCLIP-GmP-ViT-L-14"
     config = CLIPConfig.from_pretrained(model_id)
@@ -103,7 +104,7 @@ def update_selection(evt: gr.SelectData, width, height):
     )
 
 @spaces.GPU(duration=50)
-def generate_image(prompt, trigger_word, steps, seed, cfg_scale, width, height, lora_scale, progress):
+def generate_image(prompt, trigger_word, steps, seed, cfg_scale, width, height, lora_scale, progress): 
     pipe.to("cuda")
     generator = torch.Generator(device="cuda").manual_seed(seed)
     
@@ -161,7 +162,7 @@ with gr.Blocks(theme=gr.themes.Soft(), css=css) as app:
     )
     	    # Info blob stating what the app is running
     info_blob = gr.HTML(
-        """<div id="info_blob"> Img. Manufactory Running On: Our 'Historic Color SOON®' Schnell/Pixelwave-base Model (at AlekseyCalvin/HistoricColorSoonr_Schnell). Now testing related LoRAs (#s2-8,11,12,14,16)for merging. </div>"""
+        """<div id="info_blob"> Img. Manufactory Running On: ArtsyLite Flux model. Now testing related LoRAs (#s2-8,11,12,14,16)for merging. </div>"""
     )
 
         # Info blob stating what the app is running