# Face to Many - Core.Today AI API > Turn a face photo into 6 fun styles (15M+ runs) — 3D, Emoji, Video game, Pixels, Clay, or Toy. The viral avatar generator behind countless profile-picture apps. - **Provider**: fofr - **Model ID**: fofr/face-to-many - **Category**: Image Generation - **Credits**: 21 per generation - **Speed**: Fast - **Quality**: High ## Features - 6 preset styles: 3D, Emoji, Video game, Pixels, Clay, Toy - Identity preserved via InstantID - Custom LoRA support for brand styles - Single photo input ## Use Cases - Profile avatar features in apps - Community emoji packs - Marketing campaign visuals - Event badge art ## API Endpoint Base URL: https://api.core.today/v1 Create Prediction: POST /predictions Get Status: GET /predictions/{job_id} ## Authentication Header: X-API-Key: YOUR_API_KEY ## Input Parameters ### Optional - **prompt**: string (default: a person) - Optional subject description - **image**: string - Face photo to stylize - **style**: string (default: 3D) - Target style Options: 3D, Emoji, Video game, Pixels, Clay, Toy - **negative_prompt**: string - Things you do not want in the image - **denoising_strength**: number (default: 0.65) - How much to re-imagine (0-1) - **prompt_strength**: number (default: 4.5) - Strength of the prompt. This is the CFG scale, higher numbers lead to stronger prompt, lower numbers will keep more of a likeness to the original. - **control_depth_strength**: number (default: 0.8) - Strength of depth controlnet. The bigger this is, the more controlnet affects the output. - **instant_id_strength**: number (default: 1) - How strongly to preserve the face (0-1) - **seed**: integer - Random seed - **custom_lora_url**: string - Optional custom LoRA URL for your own style - **lora_scale**: number (default: 1) - How strong the LoRA will be ## Examples ### Emoji Avatar Turn a selfie into an emoji-style avatar ```json { "model": "fofr/face-to-many", "input": { "image": "https://example.com/selfie.jpg", "style": "Emoji" } } ``` ## Response Format ```json { "job_id": "abc123", "status": "pending | processing | completed | failed", "result": "URL or data (when completed)" } ``` ## Usage Flow 1. POST /predictions with model and input -> receive job_id 2. GET /predictions/{job_id} -> poll until status is completed or failed 3. Result contains output URL(s) ## Tips - Front-facing, well-lit photos give the best results - Lower instant_id_strength slightly (0.8) if the style isn't applying enough - Bring a custom LoRA to ship your own branded style - Only stylize photos of people who have consented ## Documentation https://replicate.com/fofr/face-to-many