AIが動く。未来が更新される。Qwen-Image-2.1-viggle-turbo-v0.2.1-6step-GGUF
This repository contains standalone **GGUF quantizations** of Alibaba's **Qwen-Image-2.1**, natively fused with **Viggle's v0.2.1 6-Step Turbo LoRA (Rank 256)**. By permanently fusing the high-rank distilled velocity field in FP32 prior to quantization, these checkpoints run full text-to-image generation in **just 6 steps with zero CFG**, yielding a **~4.5× speedup** while running entirely within ComfyUI's native GGUF loader.
翻訳準備中のため原文を表示しています
This repository contains standalone **GGUF quantizations** of Alibaba's **Qwen-Image-2.1**, natively fused with **Viggle's v0.2.1 6-Step Turbo LoRA (Rank 256)**. By permanently fusing the high-rank distilled velocity field in FP32 prior to quantization, these checkpoints run full text-to-image generation in **just 6 steps with zero CFG**, yielding a **~4.5× speedup** while running entirely within ComfyUI's native GGUF loader.