Category · 55 repos
Image Generation & Editing
Text-to-image, diffusion models, ComfyUI workflows and AI image editing. Ranked by star velocity over the last 24 hours.
Showing 1–50 of 55
A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
A framework for efficient model inference with omni-modality models
Project Lyra: Open Generative 3D World Models
Puts DLSS 5 neural rendering into games that never shipped it, and brings the game's own DLSS up to date - super resolution, ray reconstruction, frame generation. Scans your library, picks one of eight routes, fetches every part from its publisher at run time, then says what happened. One exe, no ad
An interactive five-chapter night walk through a Kyoto mountain temple, rendered live in Three.js.
vLLM Omni backend plugin for diffusion and multimodal generation on AWS Trainium
GGUF Quantization support for native ComfyUI models
OptiScaler bridges upscaling/frame gen across GPUs. Supports DLSS2+/XeSS/FSR2+ inputs, replaces native upscalers, enables FSR-FG/XeFG on non-FG titles. Supports Nukem mod for DLSSG-to-FSR3 FG.
Enlightened library to convert HTML and CSS to SVG
InsightCut — an AI image/video and editable Jianying draft workspace: turn scripts into storyboards, images, voiceovers, and subtitles; supports Jianying draft / CapCut draft, MP4, and asset packages.
The desktop app for ComfyUI
A precision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perfect Build Mode control, AI image generation, and fully editable PPTX. Supports the full workflow from requirements analysis and visual direction to high-quality, editable presentations.
Official repository for LTX-Video
A free, open-source framework for cinematic, interactive 3D websites with AI-generated assets (Nano Banana 2 + Meshy 7.1 on fal). 20 example sites.
Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3 & Qwen Image 2.1: train, fine-tune, profile, repair and extract LoRAs & LoKRs
Upscale manga with AI models
Art and animation, written as code. Illustrations, loops, interactive web art, launch-videos and scored films in dozens of styles, identical on every render.
Thin Intel XPU integration for upstream ComfyUI (A770/DG2 optimized custom node), extracted from intel/llm-scaler
Rethinking Generative Image Compression at Extremely Low Bitrates
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Image Editor Component for React — crop, resize, filters, draw, text, shapes, stickers, frames, and an AI Assistant
Remove visible and invisible AI watermarks and provenance metadata from images and video. Python library and CLI for SynthID, C2PA, EXIF, IPTC, XMP, and common generative-AI marks.
A powerful, ComfyUI Custom node automation suite for generating cinema-production-grade prompts explicitly formatted for the **MiniMax H3 Video Generation System**.
Diffusion-based synthetic RF signal generation to improve modulation classification
Recommendations for reliable VPN services, including NaiFei and premium services; TikTok and YouTube 4K videos load instantly; supports popular AI tools such as ChatGPT, Claude, and Midjourney
Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip selected H3 transformer evaluations, with adaptive scheduling, sampler-aware support for Euler, ER-SDE, RES, SEEDS and SA-Solver, CPU/VRAM history storage, and fail
Agent skill from Y Build for turning AI images and videos into playable game art assets
Stable Diffusion web UI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.
Generative AI satellite cloud removal system using SAR-guided diffusion bridges for ISRO LISS-IV imagery — ISRO Bharatiya Antariksh Hackathon 2026 Grand Finale Finalist
Procedural, pointer-reactive ASCII backgrounds for the web. WebGL2, zero dependencies, drop-in React.
Manga translation app powered by AI
A general-purpose window upscaler for Windows 10/11.
An open-source AI creation workspace integrating an infinite canvas, Agent, director's desk, panoramas, AI image generation, image editing, video generation, canvas composition, and more; compatible with the OpenAI interface and multiple API services
A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, INSPYRENET, BEN, BEN2, BiRefNet, SDMatte, SAM, SAM2, SAM3 and GroundingDINO.
Aliyun CAPTCHA 2.0 V3 (INPAINTING) automatic slider solver — jsdom environment spoofing + multimodal AI image recognition to locate the missing piece
Editable reference-media timeline director for ComfyUI MiniMax H3 Reference to Video
Procedural terrain generation with diffusion models (in Minecraft)
Minecraft CityGen: Turn your own Minecraft builds into an entire city.
AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.
Qwen's most powerful open-source image generation model
MiniMax H3 acceleration for ComfyUI on RTX 5090 D v2: fused INT8 kernels, Kitchen 0.2.36, reproducible benchmarks and fast VAE output.
🐳Dockerfile for 🎨ComfyUI. | Container images and startup scripts.
Wraps Muse(muse.ai) as an OpenAI-compatible API through reverse engineering, supporting chat, text-to-image, text-to-video/image-to-video, multi-account pool rotation, and automatic renewal every 48 hours. OpenAI-compatible API for Muse.ai with Chat, Image & Video generation.
Production-grade screenplay studio: converts bullet points & images into strict single-line, timecoded video prompts for MiniMax H3, Maestro, Kling & Runway. Local LM Studio vision, floorplan analysis, DE/EN GUI. Zero line breaks guaranteed.
A high-performance, fully client-side tool for removing Gemini AI image and video watermarks. Built with pure JavaScript using mathematically precise Reverse Alpha Blending.
Chat and Image Generation for a Tandy 1000 TL/3 286 PC with 16 color dithering coupled with a remote PC over a LAN connection.
Versatile audio super resolution (any -> 48kHz) with AudioSR.