WF / Guides
Guides for realtime video and world models
Practical write-ups for developers adding live AI video to a product: sessions, streaming transport, per-second cost and bringing your own model.
- Guide · 6 minChoosing a realtime video model: a decision guide for 12 hosted modelsPick between 12 hosted realtime video and world models by inputs, live controls, audio, transports, runtime status and current API prices.Updated Nov 9, 2026
- Measured engineering · 3 minEdenLive compute measurements on H100, MI355X and RTX PRO 6000Compare six archived EdenLive model-loop measurements on H100, MI355X and RTX PRO 6000, with downloadable data and explicit browser-latency limits.Updated Nov 9, 2026
- Guide · 5 minHow per-second pricing works for realtime video, with worked examplesUnderstand billable-second video API pricing, compare model rates and estimate session costs. Queueing and startup are free; release sessions to stop billing.Updated Nov 9, 2026
- Guide · 4 minHow to add live AI video to your app and pay per secondAdd live AI video to your product: choose a model, connect a session, stream frames, send controls and estimate billable session costs with Windflow.Updated Nov 9, 2026
- Evaluation guide · 3 minHow to measure realtime video API latency and responsivenessMeasure first-frame time, control-to-visible delay, delivered FPS and stalls. Evaluate a realtime video or world model through the client your users see.Updated Nov 9, 2026
- Model API guide · 8 minHow to use the Helios APIUse the Helios API from a browser: mint a token on your server, wait for ready, stage the opening prompt, draw the live stream and release the session.Updated Nov 9, 2026
- Model API guide · 9 minHow to use the LingBot APIUse the LingBot API to stream a navigable world: seed image and prompt in one call, WASD as ordered key snapshots, events mid-run and a clean release.Updated Nov 9, 2026
- Model API guide · 9 minHow to use the LongLive 2 APIUse the LongLive-2.0 API to stream a multi-shot video: stage the opening shot, start, then steer with soft shots, hard cuts and shots scheduled ahead of time.Updated Nov 9, 2026
- Model API guide · 9 minHow to use the SANA-Streaming APIEdit a live webcam or an uploaded clip with the SANA-Streaming API: one WebSocket for camera and video, an edit prompt, periodic re-anchoring and release.Updated Nov 9, 2026
- Measured engineering · 4 minJoyAI live editing latency: what the 443 ms measurement includesRead JoyAI's 443 ms result with its loopback measurement boundary. Compare frame processing and emission stages with downloadable data and sample counts.Updated Nov 9, 2026
- API guide · 3 minRealtime video API: generate, edit and control live AI videoChoose a realtime video API for continuous generation, webcam editing or interactive worlds. Compare controls, latency, session lifecycle and usage costs.Updated Nov 9, 2026
- Measured engineering · 5 minSANA camera delivery: why 25 fps can still mean a slow responseSix SANA camera runs separate native FPS, interpolated playback, buffering and visible response. Download the November 7 measurements and method.Updated Nov 9, 2026
- Guide · 6 minStreaming a video diffusion model to the browser: WebRTC or WebSocket?Deliver streaming video diffusion to the browser with WebRTC or WebSocket. Understand generation chunks, network trade-offs and visible latency.Updated Nov 9, 2026
- World model guide · 4 minWorld model API: embed a navigable AI world in your appEmbed navigable AI worlds with a hosted world model API. Compare LingBot, Matrix-Game, DreamX and ABot inputs, movement controls and integration limits.Updated Nov 9, 2026
- Prompt guide · 4 minHelios prompting guide: write and steer a live videoWrite Helios prompts that hold up in a live stream: the opening prompt, soft steering versus scene cuts, scheduled beats, reference images and image strength.Updated Nov 3, 2026
- Model API guide · 8 minHow to use the DreamX World APIUse the DreamX-World-5B API to roll a seed image forward as a world you steer: stage prompt and seed together, send movement and look state, and release.Updated Nov 3, 2026
- Model API guide · 9 minHow to use the EdenLive APIRender a game or live video with the EdenLive API: send greybox frames up one WebSocket, set a scene prompt and visual anchor, and draw the generated stream.Updated Nov 3, 2026
- Model API guide · 10 minHow to use the Hy-Nomas APIStream a Hy-Nomas world from a text prompt: open it with set_prompt, steer it with held keys and text events, and plan each world as a 60-second take.Updated Nov 3, 2026
- Model API guide · 9 minHow to use the JoyAI Video Edit APIEdit a live webcam or an uploaded clip with the JoyAI-Video-Edit API: server token, one WebSocket for camera and video, the edit instruction and release.Updated Nov 3, 2026
- Model API guide · 7 minHow to use the LTX-2.5 APIStream LTX-2.5 video with generated audio: join the session over WebRTC, play picture and sound in one element, steer window by window, and release.Updated Nov 3, 2026
- Model API guide · 8 minHow to use the Matrix-Game 4.0 APIStream a playable game re-rendered by Matrix-Game 4.0: pick a scene before start, send held-key snapshots on the socket, and plan for 60-second sessions.Updated Nov 3, 2026
- Prompt guide · 4 minHow to write edit instructions for realtime video editingWrite edit instructions that change only what you mean in a live webcam or clip: instructions not captions, what changes then what stays, and reference images.Updated Nov 3, 2026
- Prompt guide · 4 minLongLive 2 prompting guide: shots, cuts and timelinesWrite LongLive-2.0 shot prompts for a live multi-shot video: one shot per prompt, soft shots versus hard cuts, continuity anchors and a timeline planned ahead.Updated Nov 3, 2026
- Prompt guide · 4 minLTX-2.5 prompting guide: scenes, sound and dialogueWrite LTX-2.5 prompts for a live stream with sound: one audio-visual brief per ten-second window, dialogue in quotes, continuity anchors and when to cut.Updated Nov 3, 2026
- Prompt guide · 5 minWorld model seed images and prompts: a practical guidePick seed images and write prompts that keep a navigable world model stable: matching image and prompt, framing for movement, world events and control rhythm.Updated Nov 3, 2026
- Guide · 4 minHow to turn an open-source video model into a realtime APIPrepare a video model for a hosted realtime API: licensed weights, repeatable inference, streaming transport, session controls and measured performance.Updated Oct 26, 2026
- Guide · 4 minWhat is a world model? How it differs from video generationA world model predicts how an environment changes as you act in it. What that means, how it differs from video generation, what people use it for, and where it falls short.Updated Oct 26, 2026
- Troubleshooting guide · 8 minHow to recover a realtime video stream after a dropped connectionTell a dropped connection from an ended session, retry inside a bounded grace, reattach to the same session and restore playback, with a test checklist.Updated Oct 20, 2026
- Model API guide · 8 minHow to use the ABot World APIUse the ABot-World API to stream a third-person world: WebSocket-only delivery, seed image and prompt staged together, eight-key controls and release.Updated Oct 20, 2026
- Performance guide · 3 minRealtime AI video on AMD GPUs: reading MI355X benchmarksRead Windflow's AMD MI355X video inference measurements with the right context: GPU count, resolution, generated windows, edit latency and runtime limits.Updated Oct 13, 2026
- Guide · 5 minHow realtime video models work: autoregressive diffusion, chunks and the latency budgetWhy standard video diffusion cannot run live, what autoregressive chunked generation and few-step distillation change, where the latency goes, and how to read a realtime claim.Updated Oct 11, 2026