Updated app.py

app.py

@@ -1,146 +1,88 @@
 import gradio as gr
-import numpy as np
-import random
-from diffusers import DiffusionPipeline
+import spaces
 import torch
+from diffusers import DiffusionPipeline
+from PIL import Image
 
-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)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
-
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-        
-    generator = torch.Generator().manual_seed(seed)
-    
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
-    
-    return image
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
-
-with gr.Blocks(css=css) as demo:
-    
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
-        
-        with gr.Row():
-            
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-            
-            run_button = gr.Button("Run", scale=0)
-        
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-            
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
-            with gr.Row():
-                
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
+
+# Text-to-Multi-View Diffusion pipeline
+text_pipeline = DiffusionPipeline.from_pretrained(
+    "dylanebert/mvdream",
+    custom_pipeline="dylanebert/multi-view-diffusion",
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+).to("cuda")
+
+
+# Image-to-Multi-View Diffusion pipeline
+image_pipeline = DiffusionPipeline.from_pretrained(
+    "dylanebert/multi-view-diffusion",
+    custom_pipeline="dylanebert/multi-view-diffusion",
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+).to("cuda")
+
+
+def create_image_grid(images):
+    images = [Image.fromarray((img * 255).astype("uint8")) for img in images]
+
+    width, height = images[0].size
+    grid_img = Image.new("RGB", (2 * width, 2 * height))
+
+    grid_img.paste(images[0], (0, 0))
+    grid_img.paste(images[1], (width, 0))
+    grid_img.paste(images[2], (0, height))
+    grid_img.paste(images[3], (width, height))
+
+    return grid_img
+
+
+@spaces.GPU
+def text_to_mv(prompt):
+    images = text_pipeline(
+        prompt, guidance_scale=5, num_inference_steps=30, elevation=0
+    )
+    return create_image_grid(images)
+
+
+@spaces.GPU
+def image_to_mv(image, prompt):
+    image = image.astype("float32") / 255.0
+    images = image_pipeline(
+        prompt, image, guidance_scale=5, num_inference_steps=30, elevation=0
+    )
+    return create_image_grid(images)
+
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            with gr.Tab("Text Input"):
+                text_input = gr.Textbox(
+                    lines=2,
+                    show_label=False,
+                    placeholder="Enter a prompt here (e.g. 'a cat statue')",
                 )
-            
-            with gr.Row():
-                
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
+                text_btn = gr.Button("Generate Multi-View Images")
+            with gr.Tab("Image Input"):
+                image_input = gr.Image(
+                    label="Image Input",
+                    type="numpy",
                 )
-                
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
+                optional_text_input = gr.Textbox(
+                    lines=2,
+                    show_label=False,
+                    placeholder="Enter an optional prompt here",
                 )
-        
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
-        )
-
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
+                image_btn = gr.Button("Generate Multi-View Images")
+        with gr.Column():
+            output = gr.Image(label="Generated Images")
+
+    text_btn.click(fn=text_to_mv, inputs=text_input, outputs=output)
+    image_btn.click(
+        fn=image_to_mv, inputs=[image_input, optional_text_input], outputs=output
     )
 
-demo.queue().launch()
+
+if __name__ == "__main__":
+    demo.queue().launch()