Update app.py

app.py

@@ -1,153 +1,89 @@
 import gradio as gr
 import numpy as np
-import random
+from transformers import TimmWrapper 
 
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 import torch
+import torchvision.transform.v2 as T
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
 
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    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, seed
-
-
-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: 640px;
+MODEL_MAP = {
+    "hf_hub:p1atdev/style_250412.vit_base_patch16_siglip_384.v2_webli": {
+        "mean": [0, 0, 0],
+        "std": [1.0, 1.0, 1.0],
+        "image_size": 384,
+        "background": 0,
+    }
 }
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        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, variant="primary")
-
-        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)
+def config_to_processor(config: dict):
+    return T.Compose(
+        [
+            T.Resize(
+                size=None,
+                max_size=config["image_size"],
+                interpolation=T.InterpolationMode.NEAREST,
+            ),
+            T.Pad(
+                padding=config["image_size"] // 2,
+                fill=config["background]",  # black
+            ),
+            T.CenterCrop(
+                size=(config["image_size"], config["image_size"]),
+            ),
+            T.PILToTensor(),
+            T.ToDtype(dtype=torch.float32, scale=True), # 0~255 -> 0~1
+            T.Normalize(mean=config["mean"], std=config["std"]),
+        ]
+    )
 
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+def load_model(name: str):
+    return TimmWrapper.from_pretrained(name).eval().requires_grad_False)
 
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+MODELS = {
+    name: {
+        "model": load_model(name),
+        "processor": config_to_processor(config),
+    }
+    for name, config in MODEL_NAMES.items()
+}
 
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
 
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
+@torch.inference_mode()
+def calculate_similarity(model:_name str, image_1: Image.Image, image_2: Image.Image):
+    model = MODELS[model_name]["model"]
+    processor = MODELS[model_name]["processor"]
+    
+    pixel_values = torch.cat([
+        processor(image) for image in [image_1, image_2]
+    ])
+    embeddings = model(pixel_values)
+    embeddings /= embeddings.norm(p=2, dim=-1, keepdim=True)
+
+    similarity = (embeddings[0] * embeddings[1]).item()
+    return similarity
+    
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            image_1 = gr.Image("Image 1", type="pil")
+            image_2 = gr.Image("Image 2", type="pil")
+
+            model_name = gr.Dropdwon("Model", choices=list(MODELS.keys())
+            submit_btn = gr.Button("Submit", variant="primary")
+        
+        with gr.Column():
+            similarity = gr.Text("Similarity")
 
-        gr.Examples(examples=examples, inputs=[prompt])
     gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
+        triggers=[submit_btn.click],
+        fn=calculate_similarity,
         inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
+            model_name,
+            image_1,
+            image_2,
         ],
-        outputs=[result, seed],
+        outputs=[image_2],
     )
 
 if __name__ == "__main__":