Qwen-Image-LoRA-DLC
Qwen-Image model with various LoRA (Low-Rank Adaptation) styles. This tool provides both speed-optimized and quality-focused generation modes with a curated collection of artistic styles.
- 4
- Python
- Apache-2.0
- 11 mo ago
Qwen-Image model with various LoRA (Low-Rank Adaptation) styles. This tool provides both speed-optimized and quality-focused generation modes with a curated collection of artistic styles.
Synthesize macOS trackpad dock-swipe gestures from the CLI — trigger Mission Control, switch Spaces, App Exposé, Show Desktop & Launchpad through the real gesture pathway, with controllable speed. Built for end-to-end UI test automation.
VLM-Parsing is a Gradio-based web application for parsing documents and images into structured HTML and Markdown formats using advanced Vision Language Models (VLMs).
The POINTS-Reader, a vision-language model for end-to-end document conversion, is a powerful, distillation-free Vision-Language Model that sets new SoTA benchmarks.
Classifies Steam Game-Review Constructiveness
Runs in the browser on Hugging Face
Generate runnable Hugging Face repo quickstarts.
Runs in the browser on Hugging Face
MiniMax-H3-Turbo-LoRA-Fast is the denoising half of a modular, split-architecture deployment designed for high-resolution, long-form video generation (up to 20 seconds) with native audio support.
Native macOS Picture-in-Picture for Chrome & Firefox: watch YouTube, Twitch and any web video in a PiP window that stays on top of fullscreen apps and Spaces.