type-two 431aeb08ea feat(mflux_image_edit): Qwen-Image-Edit LoRA support ... mflux-generate-qwen-edit already exposes --lora-paths/--lora-scales; wire them to params.loras (['multiple-angles=1.0', ...]). Names resolve by filename stem or fuzzy match across QWEN_LORA_DIRS (default ~/Documents/localmodels/QwenLora) so John can drop new .safetensors in and use them by short name. Misses log loudly instead of failing the job. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>		2026-07-25 00:57:06 +10:00
..
manifest.json	feat(mflux_image_edit): pass ALL inputs to --image-paths — multi-image compose	2026-07-20 18:33:19 +10:00
run.py	feat(mflux_image_edit): Qwen-Image-Edit LoRA support	2026-07-25 00:57:06 +10:00