- Build CLIP with --no-build-isolation to use venv's setuptools 69.5.1
instead of pip pulling setuptools 82.0.0 (which removed pkg_resources)
into an isolated build environment
- Add cleanup_broken_packages() to remove dist-info directories with
missing RECORD files before falling back from uv to pip, preventing
cascading install failures when uv partially installs packages
- Add no_build_isolation parameter to install() function
Nunchaku's SDXL UNet does not support offloading and raises
NotImplementedError when offload=True is passed. Skip the parameter
for SDXL and log a warning instead of crashing.
Add 4-step distilled Nunchaku SVDQuant entries for Qwen-Lightning and
Qwen-Lightning-Edit alongside the existing 8-step variants. Step count
is now shown in the reference name (e.g. "Qwen-Lightning (4-step)").
- Add subfolder parameter to load_qwen_nunchaku to distinguish
4-step (nunchaku-4step) from 8-step (nunchaku) variants
- Route to correct safetensors: lightningv1.0-4steps vs
lightningv1.1-8steps for gen, lightningv1.0-4steps vs
lightningv1.0-8steps for edit
- Strip nunchaku subfolder before pipeline from_pretrained since
it does not exist in the base HuggingFace repos
Filter out reference entries tagged "nunchaku" from Extra Networks
when the active backend is not CUDA, since Nunchaku requires NVIDIA
GPUs. Entries remain in shared.reference_models for programmatic
lookup but are not yielded to the UI.
- Rename HuggingFace org from nunchaku-tech to nunchaku-ai across all
nunchaku model repos (flux, sdxl, sana, z-image, qwen, t5)
- Add per-torch-version nunchaku version mapping instead of single global
version, with robust torch version parsing
- Add 'Fill (Nunchaku)' and 'Depth (Nunchaku)' options to Flux Tools
dropdown, loading models with +nunchaku suffix for SVDQuant quantization
- Mark Fill and Depth nunchaku reference entries as hidden so they remain
available for check_nunchaku() lookup but don't appear in Extra Networks
- Filter hidden reference models in ui_extra_networks_checkpoints
Replace manual Model/TE checkboxes in Quantization Settings with a
dedicated "Nunchaku" tab in the Extra Networks menu where users can
directly select nunchaku-quantized model variants. Detection is now
using a +nunchaku path marker for disambiguation.
vladmandic
CalamitousFelicitousness
awsr
Oliver Hertel