Viggle ships 6-step distilled Qwen-Image-2.1 turbo, ~5x faster than 40-step base
_akhaliq · x · 2026-09-26
Viggle released Qwen-Image-2.1-viggle-turbo v0.2.1 on Hugging Face, a DMD-distilled LoRA (rank 256/128) that runs text-to-image and instruction-based editing in 6 steps with no CFG — roughly 5x faster than the 40-step base with near-parity quality. Dense small text and complex edits remain the weak spots; ComfyUI nodes and workflows are included.
Related event: Viggle's Distilled Qwen-Image-2.1 Generates 5x Faster in 6 Steps(2 posts)→
More from Multimodal
- Simple KJnodes workflow adds bounding-box control to Krea 2 text-to-image — Mulksky · 2026-09-26
- Leak: xAI building music composer for Grok Imagine with Replace Audio feature — nima_owji · 2026-09-26
- One Prompt Turns ChatGPT + Tesseract Into an AR UI Video Effects Generator — chrisfirst · 2026-09-26
- Mirage launches Tesseract, a video creative suite that lets AI agents edit and render video directly — chrisfirst · 2026-09-26
- Quiver Arrow 2 lands in Melius: prompt-to-SVG with editable vector paths — stuffyokodraws · 2026-09-26
- "Curve slop": critic dismisses AI animation demo as spline enumeration — ryunuck · 2026-09-26