Text to video
Start from a prompt at 16:9, 9:16, or 1:1. Run 5, 10, 15, 20 or 30 seconds at 720p or 1080p, with optional generated audio and an optional seed.
Wan 3.0 is the new Flagship for text-to-video, first-frame image-to-video, and first-plus-last-frame image-to-video. Generate audio, choose 720p or 1080p, and keep every result private by default.
First image free · video from 55 Coins · 18+
Yes. Wan 3.0 builds video from text, from one opening frame, or from an opening and a closing frame. It is priced by the second: 11 Coins a second at 720p and 18 at 1080p, so five seconds is 55 Coins or 90, and you can run to thirty seconds.
Private workflow-test output · no post-processing · opens with any confirmed payment
Start from a prompt at 16:9, 9:16, or 1:1. Run 5, 10, 15, 20 or 30 seconds at 720p or 1080p, with optional generated audio and an optional seed.
Animate an owned image from My Creations. The clip keeps that frame’s shape and framing, so write about what moves and where the camera goes, not about what she looks like.
Choose owned opening and ending images, then describe the physical path between them. Similar references create cleaner transitions.
11 Coins a second. Five seconds is 55 Coins, ten is 110, thirty is 330. The rate is the same for text-to-video and for both image-to-video modes.
18 Coins a second, so five seconds is 90 Coins. Generated audio is included either way and does not change the price.
Use text-to-video, first-frame image-to-video, or first-plus-last-frame image-to-video with the same clear Coin matrix.
Use the free adult builder, copy all three T2V and I2V templates, and fix common POV, timing, camera, and morphing problems.
Choose T2V or I2V, structure the shot, and stop writing video prompts like static image descriptions.
For I2V, solve subject, composition, lighting, and style before you animate the winner.
Everything generated here must depict fictional adults. No one under 18, no real person without that person’s explicit consent, and no non-consensual scenarios. Those rules are enforced at generation time. Read the Content Policy or use Report Content.
Yes. Text-to-video is a first-class Wan 3.0 mode at 16:9, 9:16, or 1:1.
Yes. Select an owned completed image from My Creations. You animate images you generated here; uploading a video from your camera roll is not supported.
Yes. Wan 3.0 can use both first and last owned images when their known aspect ratios match. The motion prompt describes the transition between them.
Generated audio is available and defaults on. You can disable it; the Coin price stays the same.
No. Video opens for good with any confirmed payment — a one-time Coin pack from $4.99. Video always costs Coins. There is no tier that includes it.
Eleven Coins a second at 720p and 18 at 1080p, so five seconds is 55 Coins and ten is 110. Durations run out to thirty seconds and generated audio is included in the price.
Yes, and it is the better route. Image-to-video takes your picture as the opening frame, which is what holds one face across a whole clip instead of inventing a new person on every run.
Yes. Duo Mode renders two people in a single shot with a setting and an ending you choose, at 79 Coins for 7 seconds or 119 for 15.
No. Act presets are already written and start at 21 Coins, 79 for the premium ones. For anything specific, the prompt writer turns your own sentence into a finished video prompt in eleven languages, free.
Usually a few minutes. It lands in your gallery when it is finished, and you do not have to keep the tab open waiting for it.
Images, edits, photo sets and video in one private studio. A single purchase opens every paid tool and the Rewards ladder — spend your Coins your way and download your results. Packs start at $4.99.
No membership and no renewal: Coins are a one-time purchase. Pay by card, Telegram Stars or crypto.Use the free Wan 3.0 prompter, then generate privately in Studio.
Make your first image free