Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# LivePortrait SPADE decoder, Core ML
|
| 2 |
+
|
| 3 |
+
LivePortrait's SPADE decoder (KwaiVGI) as a Core ML ML Program in float16, built with coremltools' MIL builder from [spade_generator.pth](https://huggingface.co/KlingTeam/LivePortrait/blob/main/liveportrait/base_models/spade_generator.pth)
|
| 4 |
+
|
| 5 |
+
- Input `feature`: float32 `[1, 256, 64, 64]`, the warping network's output (NCHW).
|
| 6 |
+
- Output `face`: `[1, 3, 512, 512]` in [0, 1].
|
| 7 |
+
- Instance norms read their input 256× smaller and the res-block convs 64× smaller (results scaled back): the activations reach ~10⁴, past float16 otherwise.
|
| 8 |
+
- Run it on the GPU (`.cpuAndGPU`): 32 ms on an M5, 0.15–0.21 levels mean from the float32 decoder. The Neural Engine is slower (41 ms) and 3 levels off.
|