FaceFusion 3.0.0 β Complete ONNX Model Repository
This repository contains the full, unmodified ONNX model set duplicated fromfacefusion/models-3.0.0.
All models are provided for inference only and are intended for use with FaceFusion or custom ONNX Runtime pipelines.
Each .onnx file is paired with a .hash file used for integrity verification.
General Information
- Framework: ONNX
- Origin: facefusion/models-3.0.0
- Status: Inference-ready
- Execution: CPU / CUDA / TensorRT / DirectML / CoreML (provider dependent)
- Training: Not supported
Complete List
Landmark Detection & Alignment
2dfan4.onnxfan_68_5.onnx
ArcFace / Identity Conversion
arcface_w600k_r50.onnxarcface_converter_ghost.onnxarcface_converter_simswap.onnx
Face Detection
retinaface_10g.onnxscrfd_2.5g.onnxyoloface_8n.onnx
Face Segmentation
bisenet_resnet_34.onnxdfl_xseg.onnx
Face Swapping
inswapper_128.onnxinswapper_128_fp16.onnxsimswap_256.onnxsimswap_unofficial_512.onnxuniface_256.onnxblendswap_256.onnxghost_1_256.onnxghost_2_256.onnxghost_3_256.onnx
Face Restoration & Enhancement
gfpgan_1.2.onnxgfpgan_1.3.onnxgfpgan_1.4.onnxgpen_bfr_256.onnxgpen_bfr_512.onnxgpen_bfr_1024.onnxgpen_bfr_2048.onnxrestoreformer_plus_plus.onnxcodeformer.onnx
Face Attributes / Analysis
fairface.onnxstyleganex_age.onnx
Live Portrait / Motion Transfer
live_portrait_feature_extractor.onnxlive_portrait_motion_extractor.onnxlive_portrait_eye_retargeter.onnxlive_portrait_lip_retargeter.onnxlive_portrait_generator.onnxlive_portrait_stitcher.onnx
Lip Synchronization
wav2lip_96.onnxwav2lip_gan_96.onnx
Super-Resolution & Upscaling
real_esrgan_x2.onnxreal_esrgan_x2_fp16.onnxreal_esrgan_x4.onnxreal_esrgan_x4_fp16.onnxreal_esrgan_x8.onnxreal_esrgan_x8_fp16.onnxreal_hatgan_x4.onnxultra_sharp_x4.onnxlsdir_x4.onnxnomos8k_sc_x4.onnxspan_kendata_x4.onnxclear_reality_x4.onnx
Colorization
deoldify.onnxdeoldify_artistic.onnxdeoldify_stable.onnxddcolor.onnxddcolor_artistic.onnx
Audio / Classification / Misc
kim_vocal_2.onnxopen_nsfw.onnxpeppa_wutz.onnx
Hash Files
Every model includes a corresponding .hash file:
- Ensures file integrity
- Required by FaceFusion
- Must not be removed or modified
Example Usage
import onnxruntime as ort
session = ort.InferenceSession(
"inswapper_128.onnx",
providers=["CUDAExecutionProvider", "CPUExecutionProvider"]
)
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
π
Ask for provider support