Gradio

Upload Face Image

🎛️ Action Unit Parameters

AU Parameters (JSON)

Inference Steps (20=fast/lower quality, 50=balanced, 100=slow/high quality)

20 100

Seed (for reproducibility)

⚠️ Note: Transformation takes ~10-15 minutes on CPU. Please be patient!

Transformed Result

Status

🎨 Emotion Presets (click to use):

Examples

AU Parameters (JSON)	Inference Steps (20=fast/lower quality, 50=balanced, 100=slow/high quality)	Seed (for reproducibility)

🔗 API Usage

Gradio API Endpoint

POST https://gauravvjhaa-affecto-inference.hf.space/api/predict

import requests
import base64

# Prepare image
with open("face.jpg", "rb") as f:
    image_base64 = base64.b64encode(f.read()).decode()

# Call API
response = requests.post(
    "https://gauravvjhaa-affecto-inference.hf.space/api/predict",
    json={
        "data": [
            f"data:image/jpeg;base64,{image_base64}",
            '{"AU6": 2.0, "AU12": 2.0}',
            50,  # steps
            424  # seed
        ]
    }
)

result = response.json()
# Result image is in result["data"][0]

🎭 Available Action Units (AU):

😊 Happiness:

AU6 (Cheek Raiser): 0-4 → Raises cheeks, squints eyes
AU12 (Lip Corner Puller): 0-4 → Pulls lip corners up (smile)

😢 Sadness:

AU1 (Inner Brow Raiser): 0-4 → Raises inner brows
AU4 (Brow Lowerer): 0-4 → Lowers brows (frown)
AU15 (Lip Corner Depressor): 0-4 → Pulls lip corners down

😠 Anger:

AU4 (Brow Lowerer): 0-4
AU5 (Upper Lid Raiser): 0-4
AU7 (Lid Tightener): 0-4
AU23 (Lip Tightener): 0-4

😮 Surprise:

AU1 (Inner Brow Raiser): 0-4
AU2 (Outer Brow Raiser): 0-4
AU5 (Upper Lid Raiser): 0-4
AU26 (Jaw Drop): 0-4

😨 Fear:

AU1 (Inner Brow Raiser): 0-4
AU2 (Outer Brow Raiser): 0-4
AU4 (Brow Lowerer): 0-4
AU5 (Upper Lid Raiser): 0-4
AU20 (Lip Stretcher): 0-4
AU25 (Lips Part): 0-4

📊 Example Combinations:

# Happy (smile)
{"AU6": 2.5, "AU12": 3.0}

# Sad
{"AU1": 2.0, "AU4": 2.5, "AU15": 2.5}

# Angry
{"AU4": 3.0, "AU5": 2.0, "AU7": 2.5, "AU23": 2.0}

# Surprised
{"AU1": 3.0, "AU2": 2.5, "AU5": 3.0, "AU26": 2.5}

# Fear
{"AU1": 2.5, "AU2": 2.5, "AU4": 2.0, "AU5": 3.0, "AU20": 2.0, "AU25": 2.0}

⚙️ Pipeline Details:

Face Detection → InsightFace detects face
Cropping → Crop to 512×512 with alignment
Background Extraction → BiSeNet segments face from background
Diffusion → MagicFace transforms expression
Output → 512×512 transformed face

⏱️ Performance:

CPU: ~10-15 minutes per image
GPU (T4): ~15-20 seconds per image

📝 Notes:

Input images should contain at least one face
If multiple faces, largest face is used
AU values typically range 0-4 (higher = stronger)
Seed ensures reproducibility

🎭 Affecto - MagicFace Implementation

Architecture:

This is a complete implementation of the MagicFace diffusion model for facial emotion transformation.

Components:

InsightFace: Face detection and landmark extraction
BiSeNet: Face segmentation for background extraction
Stable Diffusion 1.5: Base diffusion model
Custom UNets: ID encoder + Denoising UNet from MagicFace
Action Units: FACS-based emotion parameters

References:

MagicFace Paper: arxiv.org/abs/2408.00623
MagicFace Code: github.com/weimengting/MagicFace
HuggingFace Model: huggingface.co/mengtingwei/magicface

Project Info:

Project: Affecto - Facial Emotion Transformation System
Implementation: Complete MagicFace pipeline with preprocessing
Hardware: CPU (free tier) - upgrade to GPU for faster inference

Made by Gaurav Jha and Raj Shakya 🎓

Built using Gradio, PyTorch, and Diffusers

🎭 Affecto - Real MagicFace Emotion Transformation