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
Local and cloud GPU interference model orchestrator exposing OpenAI-compatible API from different engines
A comprehensive Codex skill for Runpod: Serverless workers, Pods, Flash, Public Endpoints, runpodctl, MCP, Python SDK, REST, GraphQL, storage, debugging, and live-doc lookup in one pragmatic workflow.
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.
LTX 2.5 serverless worker template with i2v t2v workflows and bundled frontend.
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.
RunPod Serverless Worker for the Stable Diffusion WebUI Forge API
Wan 2.2 Image-to-Video inference pipeline deployed on RunPod Serverless using a Docker-based GPU setup.
🎨 Transform specific parts of your image in WAN Image-to-Video generation for targeted character or scene adjustments with ease and precision.
Adaptation of the repository https://github.com/macalistervadim/human_ml_mask_api_parser for integration into a serverless runpod
A RunPod serverless worker for Donut (Document Understanding Transformer), NAVER's OCR-free document AI model. Donut takes a document image plus a task prompt and produces structured JSON directly — no separate OCR step, no detector pipeline. The model is small (~200M params), fast on a single GPU, and remarkably accurate on layout-driven documents
RunPod serverless endpoint for Qwen3-TTS-12Hz-1.7B-Base voice cloning: register a voice once, generate long-form speech and sentence-level SRT by voice_id. Scale-to-zero.
A general purpose rig for fine-tuning LLMs
A serverless for Runpod that will run inference using ZImage model and will take LoRA as input.
A RunPod serverless worker for Microsoft TrOCR, a HuggingFace transformer-based OCR model specialized for single-line text recognition — both printed and handwritten.
To associate your repository with the runpod-serverless topic, visit your repo's landing page and select "manage topics."