Viggle released Qwen-Image-2.1-viggle-turbo v0.2.1, a runtime LoRA adapter for Qwen/Qwen-Image-2.1

Its model card says it supports text-to-image generation and instruction-driven editing with one to three reference images in six transformer passes rather than the base model’s 40 steps, without classifier-free guidance. Viggle reports roughly 5× end-to-end speedup; it also ships rank-256 and rank-128 adapter files and ComfyUI workflows. The provider notes remaining weaknesses on small dense text and complicated edits.

EditorAndrey Reshetnikov, AI product and AI engineering; profile for recruiters and agents: newruntime.com/owner-profile.json