aszc-dev
8f94f0eea5
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/.
3.9 KiB
Example Workflows
Note
The models referenced are examples — substitute your own. Every workflow starts from a checkpoint you convert yourself (see conversion); there is no Core ML model to download.
Basic txt2img
Convert a SD1.5 checkpoint, then sample from it. CLIP and VAE come from standard ComfyUI nodes — either loaded separately or pulled from the checkpoint.
- Place a SD1.5 checkpoint in
models/checkpoints(e.g. v1-5-pruned-emaonly). - Convert Checkpoint to Core ML → queue once → a
.mlpackagelands inmodels/unet. - Load Core ML UNet (or wire the converter output straight in) → Core ML Sampler → VAE Decode.
CLIP and VAE from the checkpoint:
CLIP and VAE loaded separately — use any SD1.5-compatible
CLIP
and VAE,
placed in models/clip and models/vae:
ControlNet
Convert the checkpoint with controlnet_support = True, then wire a standard
ComfyUI ControlNet. The ControlNet model itself needs no conversion. Place it in
models/controlnet (e.g.
control_v11p_sd15_scribble).
Checkpoint conversion
The minimal conversion graph. See Convert Checkpoint to Core ML.
Conversion with LoRA
Bake LoRA(s) into the model at conversion. Read the LoRA caveats first — baked weights are immutable, and support is inconsistent per-LoRA.
LCM LoRA conversion
Chain multiple LoRA loaders to use several LoRAs with one model.
Important
Here the model goes through the Core ML Adapter and
ModelSamplingDiscreteinto the standard ComfyUI KSampler (not the Core ML Sampler).ModelSamplingDiscreteis required to sample LCM LoRAs correctly.
Loading a model with baked LoRAs
Load a model that already has LoRAs baked in. CLIP must be loaded separately and
passed through the same LoRA nodes used at conversion. Since lora_name and
strength_model are baked in, they need not be passed to the loader.
Important
As above, the model goes through the Core ML Adapter +
ModelSamplingDiscreteinto the standard KSampler.
LCM conversion with ControlNet
Convert LCM_Dreamshaper_v7 with the LCM converter, then use it with or without ControlNet.
SDXL Base + Refiner
A basic SDXL graph. Add LoRAs and ControlNets as in the SD1.5 examples; the refiner step is optional.
Models: base + text encoders, refiner, VAE.
Important
SDXL does not run on the ANE. Convert with
ORIGINALand load withCPU_AND_GPU(orCPU_ONLY). If loading hangs onCPU_AND_NE, that is the cause. See limitations.
