- Docs
- Tutorials
Learning-oriented guides
Worked examples with runnable code. Each tutorial walks one model or workflow end-to-end, from import to result, in five to thirty minutes.
Run Your First Service
Generate an image from a text prompt with the Python SDK. Ends with a saved PNG on disk.
Face Restoration
Repair and upscale faces in old or low-resolution photos with the hosted gfpgan model.
Clone Any Voice
Capture a voice embedding from a short audio clip with SpeechCraft, then synthesise new speech in th…
Lip Sync a Portrait
Turn a still portrait and a voice clip into a talking-head video with the hosted img-and-audio2video…
Reasoning with deepseek-v3
Solve a maths problem step by step and generate code from a spec with deepseek-v3 chain-of-thought.
Wrap Your Own Model
Turn a PyTorch model into a cloud API by adding the @app.endpoint decorator with APIPod.
Multi-Model Pipeline
Fan out an image generation job and a voice narration job in parallel, then gather both results.
Deploy to Cloud
Build an APIPod service into a container and run it on serverless GPU via RunPod.
Monitor and Optimize
Read execution time from runtime_info, watch cold starts, and tune GPU usage on the dashboard.
Social Media Content Pipeline
Chain a script LLM, image model, voice clone, and video render into one end-to-end content workflow.
Deploy an LLM with APIPod
Wrap a Hugging Face chat model with APIPod and serve an OpenAI-compatible /chat endpoint.
SpeechCraft
Text-to-speech and voice cloning. Bark-based, 13 languages, emotion markers. Methods: text2voice, vo…
Face2Face
Face swap and enhancement. Insightface plus GFPGAN, single-shot, no training. Methods: swap, swap_im…
Audio-Driven Face Video
Hosted image + audio to talking-head video via lucataco/img-and-audio2video.
flux-schnell
Black Forest Labs flux-schnell via Replicate. Text-to-image in four diffusion steps, 1MP output.
deepseek-v3
DeepSeek V3 reasoning LLM via Replicate. Math, code generation, and step-by-step problem solving.