Default to bundled ISNet model for ML mode#15
Merged
Conversation
Bump bg-remover to v0.8.0 (fixed ML preprocessing) and default the model + model_url to the isnet-general-use.onnx asset bundled in that release, so a fresh deploy provisions a working ML model out of the box. ML requests now produce high-quality cutouts; the binary's default normalization matches ISNet. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Default to the bundled ISNet model for ML mode
Now that
bg-removerv0.8.0 fixes the ML preprocessing (BGR→RGB, proper normalization, min-max output) and bundlesisnet-general-use.onnxas a release asset, Matte can ship a working high-quality ML model by default.bg_remover_tagdefault →v0.8.0modeldefault →isnet-general-use.onnxmodel_urldefault → the bundled asset on the bg-remover v0.8.0 release (derived from the tag)A fresh deploy's build command (
matte:provision-binary) now fetches the v0.8.0 binary and the ISNet model into the runtime, somode=mlworks out of the box and produces clean, fully-opaque cutouts. The binary's default normalization (0.5/1.0) matches ISNet, so theConverterneeds no changes.default_modeis unchanged (callers opt intoml); env vars still override every value.Gate
composer readygreen — pint clean, phpstan 0 errors, pest 33/33 (81 assertions), audit clean. matte-server suite: 32 passed, 1 env-skip.