aleleba/lightcraft
1
0
Fork 0
mirror of https://github.com/storytold/lightcraft.git synced 2026-11-10 18:39:51 -06:00
Code Issues Packages Projects Releases Wiki Activity

Rename crates to neutral dac-* codename and binaries to app/app-cli

Browse Source 
Mechanical rename right after the fork so upstream merges map cleanly.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Andrew Frahn
2026-10-10 09:43:50 +11:00
co-authored by Claude Opus 5.5
parent 88ea1a804b
commit fb097d61be
411 changed files with 4008 additions and 4199 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/denoise.md
+6 -6
View File
@@ -20,7 +20,7 @@ for a user-supplied ONNX file with a `denoise-model.json` beside it. The default
offers no model downloads. The separate `rawnind-model` Cargo feature enables the
pinned RawNIND offer only when a release's model policy permits it.
Terms must be acknowledged before installation or
download. Downloads use the shared pure-Rust `lightcraft-fetch` client, with resume,
download. Downloads use the shared pure-Rust `dac-fetch` client, with resume,
progress, cancellation, size limits and SHA-256 verification.
RawNIND's optional ONNX weights are **GPL-3.0**, as recorded in the pinned model catalog.
@@ -76,8 +76,8 @@ architecture-specific assembly in its dependencies. Tiles share the outer worker
pool. A scalar implementation checks the optimized operators on synthetic networks.
Tract is not a workspace dependency or a product feature.
CPU inference and the GPU model module are feature-gated; ordinary engine/web builds
do not compile the faer/GEMM backend. The engine depends on the inference crate only through `denoise = ["dep:lightcraft-denoise", …]`;
lightweight `lightcraft-denoise-core` metadata and cache formats remain available without inference. Pictures are capped at 100 megapixels; at most
do not compile the faer/GEMM backend. The engine depends on the inference crate only through `denoise = ["dep:dac-denoise", …]`;
lightweight `dac-denoise-core` metadata and cache formats remain available without inference. Pictures are capped at 100 megapixels; at most
four tile calls run together, chosen within the process-wide working-memory budget.
One idle CPU workspace is retained, and cache costs reserve room for the blended picture.
@@ -109,9 +109,9 @@ from the current workspace. These numbers are not a fresh benchmark of this reba
Fresh checks can be run using an already installed model and CC0 raw samples:
```text
LC_DENOISE_MODEL=<model.onnx> cargo test --release -p lightcraft-gpu --lib real_model_on_the_gpu_matches_cpu -- --ignored --nocapture
LC_DENOISE_MODEL=<model.onnx> LC_DENOISE_RAW=<corpus/raw> cargo test --release -p lightcraft-engine --features rawnind-model --test denoise_cpu -- --ignored --nocapture
LC_DENOISE_MODEL=<model.onnx> LC_DENOISE_RAW=<corpus/raw> cargo test --release -p lightcraft-engine --features rawnind-model --test denoise_real -- --ignored --nocapture
LC_DENOISE_MODEL=<model.onnx> cargo test --release -p dac-gpu --lib real_model_on_the_gpu_matches_cpu -- --ignored --nocapture
LC_DENOISE_MODEL=<model.onnx> LC_DENOISE_RAW=<corpus/raw> cargo test --release -p dac-engine --features rawnind-model --test denoise_cpu -- --ignored --nocapture
LC_DENOISE_MODEL=<model.onnx> LC_DENOISE_RAW=<corpus/raw> cargo test --release -p dac-engine --features rawnind-model --test denoise_real -- --ignored --nocapture
```
## Commands and limits