# tl2012tl/TE-Speed-QwenImage21 > A ComfyUI node plugin that speeds up Qwen Image 2.1 inference using an output-prediction strategy and step caching. It reduces generation time without changing the sampling schedule. - Magnitude: 0.7 out of 10 — Steady - Stars: 66 total · +0 stars today, ≈ 2 by evening - Star trust: star growth looks organic - Category: Generative media · Language: Python · Created: 2026-09-22 · Last push: 2026-09-24 - GitHub: https://github.com/tl2012tl/TE-Speed-QwenImage21 · Page: https://gitnova.dev/en/r/tl2012tl/TE-Speed-QwenImage21 ## Useful for - Speed up image generation in ComfyUI with the Qwen Image 2.1 model - Tune the speed-quality tradeoff via reuse_threshold and step_cache modes - Insert the node into an existing workflow between UNETLoader and KSampler ## Why it’s here - 0 stars so far today, about 2 expected by the end of the day. - The repository is 6 days old and already has 66 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #196. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 3 - Issues and pull requests: 1 - Watchers: 0 - Average over the last week: 10 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 0 ## Stars per day, last 9 days (oldest → newest, today is partial) 2026-09-20 … 2026-09-28: 0, 0, 28, 14, 11, 6, 4, 3, 0 ## Spotted in now - Top new repositories this week: #196 ## Similar by description 1. **awdqwdasdg/Comfyui-Spectrum-Qwen2.1** — 0.1 · Steady · Generative media · Python · +0 stars today, ≈ 0 by evening A custom ComfyUI node that speeds up image generation with Qwen 2.1 roughly 2x at a slight quality cost. It is inserted before the KSampler and targets low-VRAM GPUs like a 3060 12GB. Full card: https://gitnova.dev/en/r/awdqwdasdg/Comfyui-Spectrum-Qwen2.1.md 2. **rui314/mold** — 1.6 · Cooling · Developer tools · Rust · +0 stars today, ≈ 3 by evening A high-performance drop-in replacement for Unix linkers that speeds up C/C++/Rust builds by linking object files faster. Full card: https://gitnova.dev/en/r/rui314/mold.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-28 02:13 UTC, updated every 30 minutes.