No preset covers what you're imagining? Type it. Freestyle turns any prompt — or any reference image — into a live transformation on your camera feed. It's the open-ended mode of LiveGen: one text box, one reference-image slot, and the same real-time engine that powers every other effect. Write an AI video freestyle prompt, and the look lands on your live video as fast as you can describe it.
Live morph, outfit swap, and style morph are all fast because they're built on presets. Freestyle removes the presets entirely: describe anything in plain text — "eyes glowing blue," "hands on fire," "turn the room into a snowstorm" — or upload your own reference image, and LiveGen applies it live on your camera feed. No waiting for a render, no fixed menu of looks.
This is the same real-time engine behind every other LiveGen mode, opened up to custom input — so if you can describe it or show a reference image for it, you can try it live. Where the preset modes answer "make me an anime character" or "put me in a new outfit," Freestyle answers "make me whatever I can type." That makes it the mode you reach for when your idea is too specific, too weird, or too new to have its own button yet.
Freestyle works on your live feed, same as every other mode. You can also work from an uploaded video instead of a live camera.
Describe the effect you want, or show LiveGen an image to match. Combine both for tighter control.
The transformation shows up on your camera feed in real time. Adjust the prompt and see the change instantly, then share the result.
Under the hood, your camera feed streams frame by frame over WebRTC to the real-time generative model behind LiveGen. The model reads your AI video freestyle prompt (and any reference image), interprets what you asked for, and paints the result back into a standard <video> element on the page — continuously, while you move. There's no upload step, no job queue, and no export-and-download loop between typing an idea and seeing it. For the background on how live AI video generation like this actually works, see real-time generative video.
Text-command style transformations that respond to what your chat is asking for, similar to the "eyes shoot lasers" and "flame in palm" effects popularized by live AI video demos. Because you're writing a custom prompt live, you can invent a new effect mid-broadcast instead of being stuck with a fixed effect list. Pair it with AI video effects for TikTok for short-form content that doesn't look like everyone else's filter.
Test an idea instantly instead of waiting on a scripted feature. If a Freestyle prompt keeps working, it's a candidate for a saved look.
For more precise control than text alone — the image sets the overall style or character, and the text nudges the details.
Take a suggestion from chat, type it, and show the result in seconds. This is where real-time AI video effects beat pre-rendered content: the payoff happens on camera, live. That makes it a natural fit for live-stream effect sessions where the audience drives the show.
Need something that's part Live Morph, part Style Morph? Describe the combination in one prompt instead of choosing between two buttons.
Upload your own art as the reference image and drive it with text, without needing it added to a preset gallery first.
When you want a quick, structured effect without writing anything, the dedicated real-time video filter tool covers the common looks — and you can switch to Freestyle the moment you need something the presets don't have.
"Glowing blue cybernetic eyes" beats "make me look futuristic." Name the object, the color, and the material you want changed.
If the result drifts, remove a clause instead of piling on more words. Short, specific prompts are easier for the model to hold steady frame to frame.
A particular art style, a specific character, or an exact color palette is often faster to show than to spell out — and you can still layer a text prompt on top.
Consistent front lighting gives the model a stable subject to work from, which keeps a real-time effect from flickering as you move.
The whole point of a real-time AI video freestyle prompt is the fast loop — tweak a word, watch what changes, keep what works. Treat the prompt box like a live dial, not a submit button.
Prompts that recreate a real person's likeness without their consent, or that request restricted content, aren't allowed — LiveGen moderates uploads and applies its content policy.
Most "AI video" tools are batch generators: you submit a prompt, wait in a queue, and download a clip you can't change without starting over. Freestyle works the opposite way. Your AI video freestyle prompt applies to the live feed as you type it, so editing the idea and editing the video become the same action. That changes what the tool is good for — instead of planning a clip in advance, you improvise on camera, respond to a live audience, and keep the takes that land. It's live AI video generation you steer in the moment, not a render you wait on.
Because everything happens in the browser over WebRTC, there's nothing to install and nothing to download when you're done — the result is already live, and it's ready to share the instant it appears.
Your prompt applies live — no submitting a job and waiting for a result to come back.
No local AI setup, no model download, no command line — just a camera, a text box, and a browser tab, on desktop or mobile.
Freestyle shares the same real-time core as Outfit Swap, Bring to Life, and Summon, so custom prompts behave consistently with the presets you already know.
Whatever you create gets a shareable link the moment it happens, ready to post without exporting. (Free-tier exports are watermarked; paid tiers remove the watermark and add HD — verify current pricing.)
No special skill required — plain, descriptive text works. You can also skip text entirely and just upload a reference image.
It's real-time — the effect applies to your live camera feed as you type and adjust, not through a submit-and-wait render queue.
Yes. Upload any reference image and LiveGen applies its look to your live feed, with or without additional text.
Those modes are built on curated presets for speed and consistency. Freestyle uses the same real-time engine but accepts open-ended text prompts and custom images instead of a fixed preset list.
Yes — Freestyle follows LiveGen's content policy, so prompts involving real people's likeness without consent or other restricted content aren't permitted.
Specific, concrete language works best: name the exact thing you want changed, its color, and its material, and change one element at a time so the live effect stays stable.
Yes. You can edit the prompt or swap the reference image mid-session and the live output updates in real time, which is what makes it useful for reacting to chat during a broadcast.
Yes. It runs in a mobile browser the same way it does on desktop — open your camera, type a custom AI video prompt live, and watch it apply. No app install required.
Free-tier exports include a watermark; paid tiers remove it and add HD. Billing is simple — 1 credit equals 1 second of generation — and you get free credits to start. Verify current pricing for the latest details.
Open your camera and play any character live — free to start.
Start generating free