ViggleAI· @ViggleAI · X·· 8 天前AI 评分50
AI 导读
Viggle 发布面向开源社区的 Qwen-Image-2.1 turbo，名为 Viggle-Turbo，采用 DMD 蒸馏，可在 4 个采样步内完成生成和编辑，且无需 classifier-free guidance。权重已在 Hugging Face 开放，并提供 Spaces 在线体验；据称速度比完整模型快 6 倍。
正文
We launched the first Qwen-Image-2.1 turbo for the open community.
Try Viggle-Turbo, a DMD-distilled Qwen-Image-2.1 that generates and edits in 4 sampling steps, with no classifier-free guidance.
Weights: https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo
Qwen-Image-2.1 in 4 steps is here ⚡ @ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model ▶️ on Spaces https://hf.co/spaces/Viggle/Qwen-Image-2.1-viggle-turbo在 X 查看被引用的帖子
来源：ViggleAI · x.com