DraconicDragon commited on
Commit
24511a1
·
1 Parent(s): c366534

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -5,7 +5,8 @@ base_model:
5
  ---
6
 
7
 
8
- ONNX conversion of kaloscope model.
 
9
 
10
  [🤗 Space Demo](https://huggingface.co/spaces/DraconicDragon/Kaloscope-artist-style-classifier) for ONNX & PyTorch inference implementation (incl. timm+lsnet; OpenVINO accelerate CPU inference; no Triton required - refer to [ska.py](https://huggingface.co/spaces/DraconicDragon/Kaloscope-artist-style-classifier/blob/main/lsnet/ska.py) or [here](https://github.com/spawner1145/comfyui-lsnet/pull/2))
11
  Barebones standalone ONNX inference script (no timm or lsnet; scores are a tiny bit different - probably different img preprocessing): [onnx_barebones_inference.py](https://huggingface.co/DraconicDragon/Kaloscope-onnx-ema/blob/main/onnx_barebones_inference.py)
 
5
  ---
6
 
7
 
8
+ Experimental ONNX conversion of kaloscope model.
9
+ These need a re-export because i didnt specify dynamic axes during export which probably locked the model behind batch size = 1; otherwise they seem to work perfectly fine
10
 
11
  [🤗 Space Demo](https://huggingface.co/spaces/DraconicDragon/Kaloscope-artist-style-classifier) for ONNX & PyTorch inference implementation (incl. timm+lsnet; OpenVINO accelerate CPU inference; no Triton required - refer to [ska.py](https://huggingface.co/spaces/DraconicDragon/Kaloscope-artist-style-classifier/blob/main/lsnet/ska.py) or [here](https://github.com/spawner1145/comfyui-lsnet/pull/2))
12
  Barebones standalone ONNX inference script (no timm or lsnet; scores are a tiny bit different - probably different img preprocessing): [onnx_barebones_inference.py](https://huggingface.co/DraconicDragon/Kaloscope-onnx-ema/blob/main/onnx_barebones_inference.py)