ComfyUI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

RunPod serverless worker for Fooocus-API. Standalone or with network volume

The Big List of Protests - An AI-assisted Protest Flyer parser and event aggregator

Production-ready RunPod serverless endpoint and pod for Qwen-Image (20B) - Text-to-image generation with exceptional English and Chinese text rendering

Production-ready RunPod serverless endpoint for Kokoro TTS. Features high-quality text-to-speech, voice mixing, word-level timestamps, and phoneme generation. Optimized for fast cold starts and auto-scaling.

RunPod Serverless Worker for the Stable Diffusion WebUI Forge API

Runpod-LLM provides ready-to-use container scripts for running large language models (LLMs) easily on RunPod.

Streamlit web app for scheduling RunPod serverless models with automatic cronjobs to prevent cold starts. Includes Slack notifications and real-time monitoring.

Adaptation of the repository https://github.com/macalistervadim/human_ml_mask_api_parser for integration into a serverless runpod

Wan 2.2 Image-to-Video inference pipeline deployed on RunPod Serverless using a Docker-based GPU setup.

A Rust SDK implementation of the Runpod API that enables seamless integration of GPU infrastructure into your applications, workflows, and automation systems.

A runpod serverless implementing Nvidia's Multilingual Speech-to-Text Model

3DGS-Runpod: A scalable pipeline to generate 3D Gaussian Splats on RunPod. Includes implementations for Pods, Serverless, and Flash, with COLMAP and Brush training.

Headless threejs using Puppeteer

RunPod serverless worker for the vLLM AI text-gen inference. Simple, optimized and customisable.

Wan2.2 Serverless Docker Image

Enable local integration of Qwen3.5 models with ComfyUI for text generation and multimodal visual tasks, featuring automatic model management and precision control.

🎨 Transform specific parts of your image in WAN Image-to-Video generation for targeted character or scene adjustments with ease and precision.

A serverless for Runpod that will run inference using ZImage model and will take LoRA as input.

Adds diarization to faster-whisper Runpod worker