run on local

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import os
 import numpy as np
 import random
 from diffusers import DiffusionPipeline
@@ -7,14 +8,15 @@ import spaces
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else:
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
+# if torch.cuda.is_available():
+torch.cuda.max_memory_allocated(device=device)
+# pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16)
+pipe.enable_xformers_memory_efficient_attention()
+pipe = pipe.to(device)
+# else:
+#     pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
+#     pipe = pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
@@ -121,17 +123,17 @@ with gr.Blocks(css=css) as demo:
                 guidance_scale = gr.Slider(
                     label="Guidance scale",
                     minimum=0.0,
-                    maximum=10.0,
+                    maximum=20.0,
                     step=0.1,
-                    value=0.0,
+                    value=6.0,
                 )
 
                 num_inference_steps = gr.Slider(
                     label="Number of inference steps",
                     minimum=1,
-                    maximum=12,
+                    maximum=50,
                     step=1,
-                    value=2,
+                    value=20,
                 )
 
         gr.Examples(
@@ -145,4 +147,8 @@ with gr.Blocks(css=css) as demo:
         outputs = [result]
     )
 
-demo.queue().launch()
+port = 19876
+hostname = os.uname()[1]
+print(f"launch http://{hostname}:{port}")
+
+demo.queue().launch(server_name="0.0.0.0", server_port=port)

requirements.txt

@@ -1,6 +1,11 @@
+gradio==4.31.5
+spaces
 accelerate
 diffusers==0.26.3
 invisible_watermark
-torch==2.2.0
+# torch==2.2.0
+# xformers==0.0.24
+torch==2.0.1
+xformers==0.0.22
 transformers
-xformers==0.0.24
+