7 days ago
-
photo animation: generator with the largest layers stored int8
-
photo animation: two ONNX files (weights stored fp16)
-
eye contact corrector: four ONNX files (weights stored int8 / fp16)
13 days ago
-
Add files
-
update
-
update
-
update
-
photo-location-finder: files only
-
photo-location-finder: fine-tuned DINOv3-B photo location model (browser build, int8 weights), head, cell list, README, DINOv3 License
-
image-eraser and ai-image-detector: float16-stored weight variants (smaller downloads)
-
photo-to-cartoon: int8-weight variants of the three generators
-
vocal-remover: float16-stored weights of htdemucs and Spleeter 2-stems
-
Weight-only fp16 builds: MODNet (channel-padded), ISNet, Depth Anything V2 Small, DDColor-T, RIFE 4.7
-
Face swapper: smaller weight-storage variants (fp16/int8 weights, float32 compute)
-
talking-photo-examples: six short voice clips for the free talking photo examples
-
face-enhancer: int8-weights variant; face-motion: 96px mouth network (int8 weights)
-
face-enhancer: GFPGAN 1.4 with float16 weights (half the download)
17 days ago
-
Add photo-to-cartoon ONNX generators (MIT, animegan2-pytorch)
18 days ago
-
Add files using upload-large-folder tool
-
Add files using upload-large-folder tool
-
Add files using upload-large-folder tool
-
Add RIFE 4.7 ONNX (fp32, fp16) for the browser, MIT
-
Add GIS basemap (Protomaps OSM z0-6 PMTiles, Noto Sans glyphs)
-
Add files using upload-large-folder tool
-
Add files using upload-large-folder tool
-
Add files using upload-large-folder tool
-
Add files using upload-large-folder tool
21 days ago
-
Add face-landmarks-onnx: MediaPipe face detector/landmarks/blendshapes and selfie multiclass as fp16 ONNX (Apache-2.0)
-
Add image-colorizer: DDColor-T 256 fp16 ONNX (Apache-2.0)
-
Add background-remover: ISNet isnet-general-use fp16 ONNX (Apache-2.0)
23 days ago
-
Add ai-music-detector (fakeprint logistic regression, retrained by WaveSpeedAI)
-
Add ai-image-detector (4-bit ONNX of Ateeqq/ai-vs-human-image-detector, Apache-2.0)
24 days ago
-
Add MediaPipe face landmarker and selfie multiclass segmentation models (unmodified, Apache-2.0)
-
Upload 2 files
-
Delete inswapper
-
add inswapper
-
initial commit
