Local, portable GUI for Qwen3-TTS. Optimized for NVIDIA RTX 50 Series (CUDA 12.8). One-click install.
A local Gradio Web-UI for the VIBE model (https://huggingface.co/iitolstykh/VIBE-Image-Edit), supporting advanced features...
A lightweight, high‑performance local interface for **FLUX.2 Klein (4B)** by Black Forest Labs.
ComfyUI integration for SparkDiffusion sparse few-step Wan video generation, with RTX 50-series and FP8 focused support.
AI-generated RTX 5090 XBAR overclocking tool with response code for related branches/discussions. Tested only on the author's configuration. For other setups, follow the docs and use an AI agent to adapt it to your machine. Use at your own risk.
A lightweight, high-performance local interface for **FLUX.2 Klein (9B)** by Black Forest Labs. This project is specifically optimized for **NVIDIA RTX 5090** GPUs, utilizing PyTorch Nightly (CUDA 13.0) and `bfloat16` precision for maximum speed.
⚡ A lightning-fast local Gradio GUI for Z-Image-Turbo (Windows). Optimized for NVIDIA RTX 5090 (Blackwell) & CUDA 12.8.
Environment setup and build fixes for 3D Gaussian Splatting on RTX 5090 (Windows, CUDA 12.8) ; See setup instructions in README_rtx5090setup.md
A Linux service that continuously monitors the 12vhwp Connector for ASUS's flagship consumer GPU's, performing safety checks every second. If a critical threat or dangerous condition is detected, it immediately shuts down the machine to prevent potential damage or further risk.
⚡ Automated nightly builds & portable releases for lucebox (DFlash) inference server on NVIDIA CUDA (sm_75-120) and AMD ROCm 7 (Strix Halo gfx1151, RX 7900 XTX gfx1100, R9700 gfx1201) with zero-dependency $ORIGIN RPATH bundling.
1508 tok/s on a single RTX 5090 Laptop: 8 lanes x 16 tok/round, Qwen3.8-27B NVFP4, with raw engine logs
Qwen3.8 Flash Next on RTX 5090: tested 131K-context profile, MTP/PLE fixes, NUMA hardware notes and reproducible client benchmarks
A Stable Diffusion 1.x-class latent diffusion model trained from scratch on 2× RTX 5090 (Blackwell) GPUs. Full UNet (~860M params), DDPM/DDIM, LAION pipeline, DDP+BF16.
Local AI video production on RTX 5090 — FLUX.2/Wan 2.2/HunyuanVideo generation, VOID object removal, SAM3+VACE editing, RIFE+SeedVR2 4K60 finishing
High-Performance LTX-Video 2.5 Inference Stack with Docker & FastAPI. ×2.1 Speedup with NVFP4, Heretic TE, Reduced 6+2 Sigmas & Resident VRAM on RTX 4090/5090.
To associate your repository with the rtx5090 topic, visit your repo's landing page and select "manage topics."