OneDiff:开箱即用的扩散模型加速库。
lcm-lora 开源项目推荐(14 个)
lcm-lora 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 14
GitHub 共 14 个仓库,已全部展示工作流转应用、屏幕共享与悬浮视频、GPT 与 3D、语音识别与 TTS
基于PyTorch的微框架,具有一流的公民API,用于基础模型适应
Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"
Consistency Distillation with Target Timestep Selection and Decoupled Guidance
LCM LoRA
This is an experimental app for a webcam-to-AI workflow with ComfyUI.
LCM-LoRA Studio - Create a high-quality image, in an average of ONLY 4 STEPS, using just a low-end CPU or a Raspberry Pi 5.
100x faster text-guided image editing on consumer GPUs (~6s vs ~10min). Combines SSD-1B, LCM-LoRA 4-step inference, and ControlNet-Canny. Benchmarked on PIE-Bench with +23.5% CLIP score over DDIM baseline.
Converts plain-language witness descriptions into forensic face portraits in seconds. Features an NLP parsing pipeline (Groq/Llama-3), SDXL/FLUX image generation with MTCNN face validation, retry logic, and seed persistence.
Deep learning coursework benchmark for LCM-LoRA image generation, with FID/LPIPS evaluation scripts and experiment configs.
Stable Diffusion for CPU only, CLI only
Download and install Renoise for Windows 10 and 11 using automated PowerShell commands.
Real-time generative design workbench mirroring Adobe Firefly. Transforms rough sketches into high-fidelity assets in <1.2s using Latent Consistency Models & ControlNet. Features a multi-style parallel comparison engine.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 14 个项目;原始页面见 https://github.com/topics/lcm-lora。
- 该话题在 GitHub 上共有 14 个仓库, 本站收录的是其中最热门的 14 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 14 个项目累计 5090 Star,覆盖 3 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。