Model card: clarify weights version (v0.0.5 = current), correct note on community port
Browse files
README.md
CHANGED
|
@@ -27,8 +27,10 @@ networks as hand-written WebGPU/WebGL2 shaders. These ONNX files let you use the
|
|
| 27 |
anywhere ONNX Runtime runs: Python, native apps, servers, mobile, or `onnxruntime-web`.
|
| 28 |
|
| 29 |
- **License:** MIT, code *and* weights. Training data provenance: [longpipe.dev/docs/licensing](https://longpipe.dev/docs/licensing).
|
| 30 |
-
- **Weights:**
|
| 31 |
-
|
|
|
|
|
|
|
| 32 |
|
| 33 |
## Quality and speed
|
| 34 |
|
|
@@ -129,9 +131,10 @@ not in these graphs. For a single-file temporal step, see the community port bel
|
|
| 129 |
- Exported with ONNX opset 17 (`large`: opset 18). Tested with ONNX Runtime 1.23 (CPU).
|
| 130 |
- Each `face` / `flow` / `matting` file contains its own copy of the tier's encoder. The SDK shares
|
| 131 |
one encoder pass across all heads; if you need that, run the SDK.
|
| 132 |
-
- Community port: [imbcmdth/longpipe-onnx](https://github.com/imbcmdth/longpipe-onnx) converted
|
| 133 |
-
|
| 134 |
-
single-graph temporal step. Thanks! This repo is the official
|
|
|
|
| 135 |
|
| 136 |
## Links
|
| 137 |
|
|
|
|
| 27 |
anywhere ONNX Runtime runs: Python, native apps, servers, mobile, or `onnxruntime-web`.
|
| 28 |
|
| 29 |
- **License:** MIT, code *and* weights. Training data provenance: [longpipe.dev/docs/licensing](https://longpipe.dev/docs/licensing).
|
| 30 |
+
- **Weights:** the SDK's current production weights (weights release `v0.0.5`, served at
|
| 31 |
+
`cdn.longpipe.dev/models/v/0.0.5/` and used by SDK 0.0.16), exported directly from the PyTorch training
|
| 32 |
+
checkpoints that produce those files. Every ONNX file is checked against PyTorch (max abs diff ≤ 7e-5,
|
| 33 |
+
most ≤ 1e-6); see `onnx/manifest.json`.
|
| 34 |
|
| 35 |
## Quality and speed
|
| 36 |
|
|
|
|
| 131 |
- Exported with ONNX opset 17 (`large`: opset 18). Tested with ONNX Runtime 1.23 (CPU).
|
| 132 |
- Each `face` / `flow` / `matting` file contains its own copy of the tier's encoder. The SDK shares
|
| 133 |
one encoder pass across all heads; if you need that, run the SDK.
|
| 134 |
+
- Community port: [imbcmdth/longpipe-onnx](https://github.com/imbcmdth/longpipe-onnx) converted the same
|
| 135 |
+
weights by reconstructing them from the SDK's packed GPU format (xs/small/large/xl), and includes a
|
| 136 |
+
single-graph temporal step with the flow stabilizer. Thanks! This repo is the official export, made
|
| 137 |
+
directly from the training checkpoints, covering all five tiers in both orientations.
|
| 138 |
|
| 139 |
## Links
|
| 140 |
|