docs: rewrite README and split into docs/ pages#66
Open
aszc-dev wants to merge 1 commit into
Open
Conversation
Rewrite the README as a lean landing page and move depth into a docs/ folder. Correct the supported-model story and several stale facts, and answer the recurring questions from issue #21. - Convert-only is the supported path: suite-converted .mlpackage is the only supported input; drop coreml-community download guidance. - Remove all .mlmodelc / Xcode references — compilation was dropped and the loader handles .mlpackage only. - Fix compute-unit name (CPU_AND_NE, not CPU_AND_ANE) and the loader input name (coreml_name). - Document CoreMLSamplerAdvanced (previously undocumented). - Add docs/: hardware, nodes, conversion, workflows, faq, troubleshooting, limitations (with a support matrix). - Note conversion now lives in the coreml-diffusion package. - Remove dev scaffolding specs; ignore *.log, .DS_Store, .claude/.
aszc-dev
commented
Jun 4, 2026
| inputs, and outputs are unchanged, so the split has effectively no user-facing | ||
| impact beyond `pip install` pulling one more dependency. | ||
|
|
||
| One detail: the LCM converter still imports `diffusers` directly (in |
Owner
Author
There was a problem hiding this comment.
Do we need LCM converter to do that still?
|
|
||
| ### Resolution crossover | ||
|
|
||
| ANE shines at small latents; the GPU scales better as resolution grows. In user |
Owner
Author
There was a problem hiding this comment.
pls verify with results: https://log.aszc.dev/ane-vs-gpu-mps-sd15-unet-energy/
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Rewrite the README as a lean landing page (453 → 113 lines) and move depth into a
docs/folder. Corrects the supported-model story and several stale facts, and answers the recurring questions from #21.Key corrections
.mlpackageis the only supported input; removed all "download from coreml-community" guidance..mlmodelc/ Xcode — compilation was removed and didn't work with the inference backend; the loader handles.mlpackageonly.CPU_AND_NE(the README previously saidCPU_AND_ANE), and the loader input iscoreml_name.CoreMLSamplerAdvanced— previously shipped but undocumented.New
docs/pageshardware.md— ANE vs GPU vs MPS, compute units, attention impls, resolution crossover, SDXL-on-ANEnodes.md— full reference for all 7 nodesconversion.md— convert-only rationale, name-based caching, quantizationworkflows.md— example gallery (basic txt2img reworked to convert-your-own)faq.md— issue More questions/clarifications for the documentation #21 answers + tracker questionstroubleshooting.md— error→fix table mined from the issue trackerlimitations.md— support matrix + expanded limitsHousekeeping
conversion now lives in the coreml-diffusion packageis reflected throughout.CONVERTER_EXTRACTION_SPEC.md,seam.md);.gitignorenow covers*.log,.DS_Store,.claude/.Notes for review
assets/are unchanged — if any depicted a downloaded Core ML model, they may warrant re-capturing, but image contents weren't inspectable.