feat: simple prediction

app_mcp.py

@@ -3,6 +3,8 @@ import time
 from typing import Literal
 import spaces
 import gradio as gr
+from gradio_client import Client, handle_file
+
 from transformers import pipeline, AutoImageProcessor, SwinForImageClassification, Swinv2ForImageClassification, AutoFeatureExtractor, AutoModelForImageClassification
 from torchvision import transforms
 import torch
@@ -90,7 +92,6 @@ MODEL_PATHS = {
     "model_3": "Organika/sdxl-detector",
     "model_4": "cmckinle/sdxl-flux-detector_v1.1",
     "model_5": "prithivMLmods/Deep-Fake-Detector-v2-Model",
-    "model_5b": "prithivMLmods/Deepfake-Detection-Exp-02-22",
     "model_6": "ideepankarsharma2003/AI_ImageClassification_MidjourneyV6_SDXL",
     "model_7": "date3k2/vit-real-fake-classification-v4"
 }
@@ -101,7 +102,6 @@ CLASS_NAMES = {
     "model_3": ['AI', 'Real'],
     "model_4": ['AI', 'Real'],
     "model_5": ['Realism', 'Deepfake'],
-    "model_5b": ['Real', 'Deepfake'],
     "model_6": ['ai_gen', 'human'],
     "model_7": ['Fake', 'Real'],
 
@@ -196,11 +196,6 @@ register_model_with_metadata(
     display_name="Vit Based", contributor="prithivMLmods", model_path=MODEL_PATHS["model_5"]
 )
 
-clf_5b = pipeline("image-classification", model=MODEL_PATHS["model_5b"], device=device)
-register_model_with_metadata(
-    "model_5b", clf_5b, preprocess_resize_224, postprocess_pipeline, CLASS_NAMES["model_5b"],
-    display_name="Vit Based, Newer Dataset", contributor="prithivMLmods", model_path=MODEL_PATHS["model_5b"]
-)
 
 image_processor_6 = AutoImageProcessor.from_pretrained(MODEL_PATHS["model_6"], use_fast=True)
 model_6 = SwinForImageClassification.from_pretrained(MODEL_PATHS["model_6"]).to(device)
@@ -252,7 +247,7 @@ def infer(image: Image.Image, model_id: str, confidence_threshold: float = 0.75)
 
 def predict_image(img, confidence_threshold):
     model_ids = [
-        "model_1", "model_2", "model_3", "model_4", "model_5", "model_5b", "model_6", "model_7"
+        "model_1", "model_2", "model_3", "model_4", "model_5", "model_6", "model_7"
     ]
     results = [infer(img, model_id, confidence_threshold) for model_id in model_ids]
     return img, results
@@ -488,6 +483,14 @@ def predict_with_ensemble(img, confidence_threshold, augment_methods, rotate_deg
 
     return img_pil, cleaned_forensics_images, table_rows, json_results, consensus_html
 
+def simple_prediction(img):
+    client = Client("aiwithoutborders-xyz/OpenSight-Community-Forensics-Preview")
+    result = client.predict(
+            input_image=handle_file(img),
+            api_name="/simple_predict"
+    )
+    return result
+
 with gr.Blocks(css="#post-gallery { overflow: hidden !important;} .grid-wrap{ overflow-y: hidden !important;} .ms-gr-ant-welcome-icon{ height:unset !important;} .tabs{margin-top:10px;}") as demo:
 
     with gr.Tab("👀 Detection Models Eval / Playground"):
@@ -553,7 +556,14 @@ with gr.Blocks(css="#post-gallery { overflow: hidden !important;} .grid-wrap{ ov
         gr.load("aiwithoutborders-xyz/OpenSight-Community-Forensics-Preview", src="spaces")
     with gr.Tab("🥇 Leaderboard"):
         gr.Markdown("# AI Generated / Deepfake Detection Models Leaderboard: Soon™")
-        
+    with gr.Tab("Simple Predict", visible=False):
+        gr.Interface(
+            fn=simple_prediction,
+            inputs=gr.Image(type="filepath"),
+            outputs=gr.Text(),
+            title="Simple and Fast Prediction",
+            description=""
+        )
     with gr.Tab("Wavelet Blocking Noise Estimation", visible=False):
         gr.Interface(
             fn=wavelet_blocking_noise_estimation,

requirements.txt

@@ -1,5 +1,6 @@
 gradio[mcp]
 gradio_leaderboard
+gradio_client
 transformers
 huggingface_hub[hf_xet]
 torchvision