automatic/data
CalamitousFelicitousness 33de04a0c7 feat: add 4-step Nunchaku variants for Qwen-Lightning models
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
2026-02-07 22:27:05 +00:00
..
previews.json relocate all jsons to data 2026-01-24 13:54:40 +01:00
reference-cloud.json relocate all jsons to data 2026-01-24 13:54:40 +01:00
reference-community.json feat: add Anima to community reference models 2026-02-02 00:44:51 +00:00
reference-distilled.json Z-Image Turbo move back to reference from distilled 2026-01-27 22:39:17 +00:00
reference-nunchaku.json feat: add 4-step Nunchaku variants for Qwen-Lightning models 2026-02-07 22:27:05 +00:00
reference-quant.json relocate all jsons to data 2026-01-24 13:54:40 +01:00
reference.json Z-Image Turbo move back to reference from distilled 2026-01-27 22:39:17 +00:00
upscalers.json relocate all jsons to data 2026-01-24 13:54:40 +01:00