Agents-MCP-Hackathon/mcp-deepfake-forensics

Update README.md

Merge remote-tracking branch 'upstream/main' into main

Update README.md

fix: model 8 inference

major(feat): add support for Gradio API model and enhance ONNX model handling

fix: model 3 config

chore: update .gitignore to include additional inference logs directory

ui(minor): add back footer

major(refactor): overhaul for ONNX and other optimizations

Update README.md

Update README.md

Update app_mcp.py

Update app.py

Update requirements.txt

Update app.py

Update app.py

custom server we go... soon (#3)

lol: disclaimer added

minor adjustments

oof...

less load: inference shouldn't take longer than 3 seconds...

hot-fix: memory (#2)

feat: enhance predict function with detailed docstring and add queue to demo interface

refactor: comment out agent logs textbox and update tab titles in demo interface

Upload model_1_quantized.onnx

Merge branch 'main' of https://huggingface.co/spaces/LPX55/mcp-deepfake-forensics

feat: integrate ONNX model inference and logging enhancements, add contextual intelligence and forensic anomaly detection agents

Create preview/.gitkeep (#1)

Update README.md

Update README.md

Update app.py

Update README.md

refactor: comment out simple prediction interface and restore community forensics preview in demo

feat: restore and enable simple prediction interface in demo, replacing community forensics preview

refactor: update consensus display in full_prediction function for improved readability

feat: add flowchart representation of image prediction process and enhance README with flowchart and multi-model consensus methods overview

refactor: update augmentation methods in full_prediction function and revise README for clarity on parameters and new functionality

yolo

feat: add image augmentation tool and update demo interface to include new functionality

refactor: remove unnecessary preprocessing function and streamline image handling in simple_prediction

fix: correct image handling in simple_prediction function and add debug prints for image types

refactor: comment out simple prediction interface and update demo tab titles for clarity

feat: improve image loading and anomaly detection in smart agents, enhancing error handling and mock anomaly generation

feat: refactor prediction functions and enhance image loading capabilities for improved processing and noise estimation

feat: enhance image handling in predictions and dynamically configure model weights based on MODEL_REGISTRY

Revert "feat: dynamically initialize model weights using MODEL_REGISTRY and adjust weights for specific models"

Revert "feat: implement universal image loader to support various input types and update preprocessing functions accordingly"

feat: implement universal image loader to support various input types and update preprocessing functions accordingly

feat: dynamically initialize model weights using MODEL_REGISTRY and adjust weights for specific models

chore: update .gitignore to include additional Python bytecode files and inference log directories