Automatic1111 serverless worker.

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

RunPod Serverless Worker for Face Swapper and Restoration powered by insightface 🔥

RunPod Serverless Worker for the ComfyUI Stable Diffusion API

RunPod Serverless Worker for the Automatic1111 Stable Diffusion API

RunPod Serverless Worker for Real-ESRGAN Restoration and Upscaling

Getting started with a serverless endpoint on RunPod by creating a custom worker

Serverless RVC endpoint for Runpod

please use https://github.com/runpod-workers/worker-faster_whisper

RunPod Serverless Worker for the Stable Diffusion WebUI Forge API

RunPod Serverless Worker for Oobabooga Text Generation API for LLMs

InstantID : Zero-shot Identity-Preserving Generation in Seconds | RunPod Serverless Worker

LLaVA: Large Language and Vision Assistant | RunPod Serverless Worker

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

Serverless GPU Stable Diffusion XL worker for Runpod, powered by diffusers. Generate images from text, transform existing images, or inpaint masked regions — all from a single serverless endpoint. Supports SDXL Base 1.0, SDXL Turbo, SDXL Lightning, Juggernaut XL, Playground V2, plus the official SDXL refiner for a final detail pass.

Serverless CPU-only MediaPipe Tasks worker covering the full vision catalog through a single endpoint: pose estimation, hand landmarks, face mesh, holistic (pose + hands + face), object detection, image segmentation, and gesture recognition — plus an annotation mode that overlays everything onto the input image.

Serverless GPU worker that turns a text prompt into a short video clip using AnimateDiff — a research-grade motion module that bolts onto any Stable Diffusion 1.5 or SDXL checkpoint and gives it temporal awareness. Served via the diffusers library on Runpod serverless. Pick a base model, pick a motion adapter, optionally stack a camera-motion LoR

Serverless speech-enhancement worker for RunPod, built on DeepFilterNet3 — a real-time deep-learning noise suppressor that consistently tops the DNS-Challenge / VCTK / VoiceBank-DEMAND benchmarks while running CPU-fast.

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

vLLM middleware that wrap RunPod-style endpoints so you can proxy fine-tuning requests from OpenAI SDK, launch jobs, and shuttle training artifacts through an S3-compatible store for custom vLLM fine-tuning workflows.