Add Krea 2 two-image i2i workflows (turbo + raw)

Add Krea 2 workflows (raw/turbo t2i + turbo i2i, optional LoRA placeholder)

Add qwen-edit-turbo-v2.json (full-precision text encoder + 8-step Lightning LoRA)

Add qwen-edit-turbo-v2.json (full-precision text encoder + 8-step Lightning LoRA)

Add remaining API-format workflows; converter fixes (subgraph promoted inputs, rgthree loras, undeclared seed-control widgets)

Add API scripts (upload/download/run/convert) and API-format headswap workflow

Upload 3 files

Delete workflows/qwen-loras-very-good-nsfw.json

Delete workflows/qwen-edit-nsfw.json

Delete workflows/qwen-loras-very-good-nsfw-v2.json

Delete workflows/qwen-loras-very-good-nsfw-v3.json

v3: exact-mirror qwen-edit-nsfw settings (same negative prompt), Qwen4Play at 0.65 — settings verified identical by structural diff

v3: restore second reference-image input (dropped upstream in qwen-edit-nsfw), expand negative prompt

add qwen-loras-very-good-nsfw-v3: Rapid-AIO 8-step pipeline (Clownshark sampler, negative prompt, CFGNorm) with Qwen4Play_v2 lora, no Lightning distill

Upload qwen-edit-nsfw.json

Delete workflows/qwen-edit-nsfw.json

head-swap-flux-klein: chain lissie_flux2_klein lora after bfs_head so the download script fetches it

Add qwen-loras-very-good-nsfw-v2 workflow (explicit output resolution control)

Add current workflows (head-swap-flux-klein, qwen-edit-nsfw w/ fixed lora path, qwen-loras)