Update app.py

app.py

@@ -37,7 +37,7 @@ main_pipe = StableDiffusionControlNetPipeline.from_pretrained(
     vae=vae,
     safety_checker=None,
     torch_dtype=torch.float16,
-).to(device)
+).to("cuda")
 
 #main_pipe.unet = torch.compile(main_pipe.unet, mode="reduce-overhead", fullgraph=True)
 #main_pipe.unet.to(memory_format=torch.channels_last)
@@ -45,7 +45,6 @@ main_pipe = StableDiffusionControlNetPipeline.from_pretrained(
 #model_id = "stabilityai/sd-x2-latent-upscaler"
 image_pipe = StableDiffusionControlNetImg2ImgPipeline(**main_pipe.components)
 
-
 #image_pipe.unet = torch.compile(image_pipe.unet, mode="reduce-overhead", fullgraph=True)
 #upscaler = StableDiffusionLatentUpscalePipeline.from_pretrained(model_id, torch_dtype=torch.float16)
 #upscaler.to("cuda")
@@ -105,13 +104,12 @@ def check_inputs(prompt: str, control_image: Image.Image):
         raise gr.Error("Prompt is required")
 
 def convert_to_pil(base64_image):
-    pil_image = Image.open(base64_image)
+    pil_image = processing_utils.decode_base64_to_image(base64_image)
     return pil_image
 
 def convert_to_base64(pil_image):
-    with tempfile.NamedTemporaryFile(suffix='.png', delete=False) as temp_file:
-        image.save(temp_file.name)
-    return temp_file.name
+    base64_image = processing_utils.encode_pil_to_base64(pil_image)
+    return base64_image
 
 # Inference function
 @spaces.GPU
@@ -143,7 +141,7 @@ def inference(
 
     main_pipe.scheduler = SAMPLER_MAP[sampler](main_pipe.scheduler.config)
     my_seed = random.randint(0, 2**32 - 1) if seed == -1 else seed
-    generator = torch.Generator(device=device).manual_seed(my_seed)
+    generator = torch.Generator(device="cuda").manual_seed(my_seed)
     
     out = main_pipe(
         prompt=prompt,
@@ -195,6 +193,87 @@ def inference(
     )
 
     return out_image["images"][0], gr.update(visible=True), gr.update(visible=True), my_seed
+        
+with gr.Blocks() as app:
+    gr.Markdown(
+        '''
+        <center><h1>Illusion Diffusion HQ 🌀</h1></span>  
+        <span font-size:16px;">Generate stunning high quality illusion artwork with Stable Diffusion</span>  
+        </center>
+ 
+        A space by AP [Follow me on Twitter](https://twitter.com/angrypenguinPNG) with big contributions from [multimodalart](https://twitter.com/multimodalart)
+        This project works by using [Monster Labs QR Control Net](https://huggingface.co/monster-labs/control_v1p_sd15_qrcode_monster).
+        Given a prompt and your pattern, we use a QR code conditioned controlnet to create a stunning illusion! Credit to: [MrUgleh](https://twitter.com/MrUgleh) for discovering the workflow :)
+        '''
+    )
+    state_img_input = gr.State()
+    state_img_output = gr.State()
+    with gr.Row():
+        with gr.Column():
+            control_image = gr.Image(label="Input Illusion", type="pil", elem_id="control_image")
+            controlnet_conditioning_scale = gr.Slider(minimum=0.0, maximum=5.0, step=0.01, value=0.8, label="Illusion strength", elem_id="illusion_strength", info="ControlNet conditioning scale")
+            gr.Examples(examples=["checkers.png", "checkers_mid.jpg", "pattern.png", "ultra_checkers.png", "spiral.jpeg", "funky.jpeg" ], inputs=control_image)
+            prompt = gr.Textbox(label="Prompt", elem_id="prompt", info="Type what you want to generate", placeholder="Medieval village scene with busy streets and castle in the distance")
+            negative_prompt = gr.Textbox(label="Negative Prompt", info="Type what you don't want to see", value="low quality", elem_id="negative_prompt")
+            with gr.Accordion(label="Advanced Options", open=False):
+                guidance_scale = gr.Slider(minimum=0.0, maximum=50.0, step=0.25, value=7.5, label="Guidance Scale")
+                sampler = gr.Dropdown(choices=list(SAMPLER_MAP.keys()), value="Euler")
+                control_start = gr.Slider(minimum=0.0, maximum=1.0, step=0.1, value=0, label="Start of ControlNet")
+                control_end = gr.Slider(minimum=0.0, maximum=1.0, step=0.1, value=1, label="End of ControlNet")
+                strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.1, value=1, label="Strength of the upscaler")
+                seed = gr.Slider(minimum=-1, maximum=9999999999, step=1, value=-1, label="Seed", info="-1 means random seed")
+                used_seed = gr.Number(label="Last seed used",interactive=False)
+            run_btn = gr.Button("Run")
+        with gr.Column():
+            result_image = gr.Image(label="Illusion Diffusion Output", interactive=False, elem_id="output")
+            with gr.Group(elem_id="share-btn-container", visible=False) as share_group:
+                community_icon = gr.HTML(community_icon_html)
+                loading_icon = gr.HTML(loading_icon_html)
+                share_button = gr.Button("Share to community", elem_id="share-btn")
+
+    prompt.submit(
+        check_inputs,
+        inputs=[prompt, control_image],
+        queue=False
+    ).success(
+        convert_to_pil,
+        inputs=[control_image],
+        outputs=[state_img_input],
+        queue=False,
+        preprocess=False,
+    ).success(
+        inference,
+        inputs=[state_img_input, prompt, negative_prompt, guidance_scale, controlnet_conditioning_scale, control_start, control_end, strength, seed, sampler],
+        outputs=[state_img_output, result_image, share_group, used_seed]
+    ).success(
+        convert_to_base64,
+        inputs=[state_img_output],
+        outputs=[result_image],
+        queue=False,
+        postprocess=False
+    )
+    run_btn.click(
+        check_inputs,
+        inputs=[prompt, control_image],
+        queue=False
+    ).success(
+        convert_to_pil,
+        inputs=[control_image],
+        outputs=[state_img_input],
+        queue=False,
+        preprocess=False,
+    ).success(
+        inference,
+        inputs=[state_img_input, prompt, negative_prompt, guidance_scale, controlnet_conditioning_scale, control_start, control_end, strength, seed, sampler],
+        outputs=[state_img_output, result_image, share_group, used_seed]
+    ).success(
+        convert_to_base64,
+        inputs=[state_img_output],
+        outputs=[result_image],
+        queue=False,
+        postprocess=False
+    )
+    share_button.click(None, [], [], js=share_js)
 
 def greet(name):
     return "Hello " + name + "!!"