Changed Generator Device

app.py

@@ -1,161 +1,161 @@
-import sys
-sys.path.append('./')
-
-import torch
-import random
-import spaces
-import gradio as gr
-
-from diffusers import AutoPipelineForText2Image
-from diffusers.utils import load_image
-
-# global variable
-device = "cuda" if torch.cuda.is_available() else "cpu"
-dtype = torch.float16 if str(device).__contains__("cuda") else torch.float32
-
-def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
-    if randomize_seed:
-        seed = random.randint(0, 2000)
-    return seed
-
-pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=dtype).to(device)
-pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
-
-@spaces.GPU(enable_queue=True)
-def create_image(image_pil,
-                 prompt,
-                 n_prompt,
-                 scale, 
-                 control_scale, 
-                 guidance_scale,
-                 num_inference_steps,
-                 seed,
-                 target="Load only style blocks",
-                 ):
-
-    
-    if target !="Load original IP-Adapter":
-        if target=="Load only style blocks":
-            scale = {
-                "up": {"block_0": [0.0, control_scale, 0.0]},
-            }
-        elif target=="Load only layout blocks":
-            scale = {
-                "down": {"block_2": [0.0, control_scale]},
-            }
-        elif target == "Load style+layout block":
-            scale = {
-                "down": {"block_2": [0.0, control_scale]},
-                "up": {"block_0": [0.0, control_scale, 0.0]},
-            }
-        pipeline.set_ip_adapter_scale(scale)
-    
-    print(image_pil)
-    
-    style_image = load_image(image_pil)
-
-    generator = torch.Generator(device="cpu").manual_seed(randomize_seed_fn(seed, False))
-    image = pipeline(
-        prompt=prompt,
-        ip_adapter_image=style_image,
-        negative_prompt=n_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        generator=generator,
-    )
-    return image
-    
-
-# Description
-title = r"""
-<h1 align="center">InstantStyle</h1>
-"""
-
-description = r"""
-How to use:<br>
-1. Upload a style image.
-2. Set stylization mode, only use style block by default.
-2. Enter a text prompt, as done in normal text-to-image models.
-3. Click the <b>Submit</b> button to begin customization.
-4. Share your stylized photo with your friends and enjoy! 😊
-
-
-Advanced usage:<br>
-1. Click advanced options.
-2. Upload another source image for image-based stylization using ControlNet.
-3. Enter negative content prompt to avoid content leakage.
-"""
-
-article = r"""
----
-```bibtex
-@article{wang2024instantstyle,
-  title={InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation},
-  author={Wang, Haofan and Wang, Qixun and Bai, Xu and Qin, Zekui and Chen, Anthony},
-  journal={arXiv preprint arXiv:2404.02733},
-  year={2024}
-}
-```
-"""
-
-block = gr.Blocks().queue(max_size=10, api_open=True)
-with block:
-    
-    # description
-    gr.Markdown(title)
-    gr.Markdown(description)
-    
-    with gr.Tabs():
-        with gr.Row():
-            with gr.Column():
-                
-                with gr.Row():
-                    with gr.Column():
-                        image_pil = gr.Image(label="Style Image", type="pil")
-                
-                target = gr.Radio(["Load only style blocks", "Load only layout blocks","Load style+layout block", "Load original IP-Adapter"], 
-                                  value="Load only style blocks",
-                                  label="Style mode")
-                
-                prompt = gr.Textbox(label="Prompt",
-                                    value="a cat, masterpiece, best quality, high quality")
-                
-                scale = gr.Slider(minimum=0,maximum=2.0, step=0.01,value=1.0, label="Scale")
-                
-                with gr.Accordion(open=False, label="Advanced Options"):
-                    
-                    control_scale = gr.Slider(minimum=0,maximum=1.0, step=0.01,value=0.5, label="Controlnet conditioning scale")
-                    
-                    n_prompt = gr.Textbox(label="Neg Prompt", value="text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry")
-                    guidance_scale = gr.Slider(minimum=1,maximum=15.0, step=0.01,value=5.0, label="guidance scale")
-                    num_inference_steps = gr.Slider(minimum=5,maximum=50.0, step=1.0,value=20, label="num inference steps")
-                    seed = gr.Slider(minimum=-1000000,maximum=1000000,value=1, step=1, label="Seed Value")
-                    randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-                    
-                generate_button = gr.Button("Generate Image")
-                
-            with gr.Column():
-                generated_image = gr.Gallery(label="Generated Image")
-
-        generate_button.click(
-            fn=randomize_seed_fn,
-            inputs=[seed, randomize_seed],
-            outputs=seed,
-            queue=False,
-            api_name=False,
-        ).then(
-            fn=create_image,
-            inputs=[image_pil,
-                    prompt,
-                    n_prompt,
-                    scale, 
-                    control_scale, 
-                    guidance_scale,
-                    num_inference_steps,
-                    seed,
-                    target], 
-            outputs=[generated_image])
-    
-    gr.Markdown(article)
-
+import sys
+sys.path.append('./')
+
+import torch
+import random
+import spaces
+import gradio as gr
+
+from diffusers import AutoPipelineForText2Image
+from diffusers.utils import load_image
+
+# global variable
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float16 if str(device).__contains__("cuda") else torch.float32
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, 2000)
+    return seed
+
+pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=dtype).to(device)
+pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
+
+@spaces.GPU(enable_queue=True)
+def create_image(image_pil,
+                 prompt,
+                 n_prompt,
+                 scale, 
+                 control_scale, 
+                 guidance_scale,
+                 num_inference_steps,
+                 seed,
+                 target="Load only style blocks",
+                 ):
+
+    
+    if target !="Load original IP-Adapter":
+        if target=="Load only style blocks":
+            scale = {
+                "up": {"block_0": [0.0, control_scale, 0.0]},
+            }
+        elif target=="Load only layout blocks":
+            scale = {
+                "down": {"block_2": [0.0, control_scale]},
+            }
+        elif target == "Load style+layout block":
+            scale = {
+                "down": {"block_2": [0.0, control_scale]},
+                "up": {"block_0": [0.0, control_scale, 0.0]},
+            }
+        pipeline.set_ip_adapter_scale(scale)
+    
+    print(image_pil)
+    
+    style_image = load_image(image_pil)
+
+    generator = torch.Generator(device=device).manual_seed(randomize_seed_fn(seed, False))
+    image = pipeline(
+        prompt=prompt,
+        ip_adapter_image=style_image,
+        negative_prompt=n_prompt,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        generator=generator,
+    )
+    return image
+    
+
+# Description
+title = r"""
+<h1 align="center">InstantStyle</h1>
+"""
+
+description = r"""
+How to use:<br>
+1. Upload a style image.
+2. Set stylization mode, only use style block by default.
+2. Enter a text prompt, as done in normal text-to-image models.
+3. Click the <b>Submit</b> button to begin customization.
+4. Share your stylized photo with your friends and enjoy! 😊
+
+
+Advanced usage:<br>
+1. Click advanced options.
+2. Upload another source image for image-based stylization using ControlNet.
+3. Enter negative content prompt to avoid content leakage.
+"""
+
+article = r"""
+---
+```bibtex
+@article{wang2024instantstyle,
+  title={InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation},
+  author={Wang, Haofan and Wang, Qixun and Bai, Xu and Qin, Zekui and Chen, Anthony},
+  journal={arXiv preprint arXiv:2404.02733},
+  year={2024}
+}
+```
+"""
+
+block = gr.Blocks().queue(max_size=10, api_open=True)
+with block:
+    
+    # description
+    gr.Markdown(title)
+    gr.Markdown(description)
+    
+    with gr.Tabs():
+        with gr.Row():
+            with gr.Column():
+                
+                with gr.Row():
+                    with gr.Column():
+                        image_pil = gr.Image(label="Style Image", type="pil")
+                
+                target = gr.Radio(["Load only style blocks", "Load only layout blocks","Load style+layout block", "Load original IP-Adapter"], 
+                                  value="Load only style blocks",
+                                  label="Style mode")
+                
+                prompt = gr.Textbox(label="Prompt",
+                                    value="a cat, masterpiece, best quality, high quality")
+                
+                scale = gr.Slider(minimum=0,maximum=2.0, step=0.01,value=1.0, label="Scale")
+                
+                with gr.Accordion(open=False, label="Advanced Options"):
+                    
+                    control_scale = gr.Slider(minimum=0,maximum=1.0, step=0.01,value=0.5, label="Controlnet conditioning scale")
+                    
+                    n_prompt = gr.Textbox(label="Neg Prompt", value="text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry")
+                    guidance_scale = gr.Slider(minimum=1,maximum=15.0, step=0.01,value=5.0, label="guidance scale")
+                    num_inference_steps = gr.Slider(minimum=5,maximum=50.0, step=1.0,value=20, label="num inference steps")
+                    seed = gr.Slider(minimum=-1000000,maximum=1000000,value=1, step=1, label="Seed Value")
+                    randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+                    
+                generate_button = gr.Button("Generate Image")
+                
+            with gr.Column():
+                generated_image = gr.Gallery(label="Generated Image")
+
+        generate_button.click(
+            fn=randomize_seed_fn,
+            inputs=[seed, randomize_seed],
+            outputs=seed,
+            queue=False,
+            api_name=False,
+        ).then(
+            fn=create_image,
+            inputs=[image_pil,
+                    prompt,
+                    n_prompt,
+                    scale, 
+                    control_scale, 
+                    guidance_scale,
+                    num_inference_steps,
+                    seed,
+                    target], 
+            outputs=[generated_image])
+    
+    gr.Markdown(article)
+
 block.launch(show_error=True)